Siga este link para ver outros tipos de publicações sobre o tema: Federate learning.
Teses / dissertações sobre o tema "Federate learning"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores trabalhos (teses / dissertações) para estudos sobre o assunto "Federate learning".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja as teses / dissertações das mais diversas áreas científicas e compile uma bibliografia correta.
1
Eriksson, Henrik. "Federated Learning in Large Scale Networks : Exploring Hierarchical Federated Learning". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-292744.
Texto completo da fonteResumo:
Federated learning faces a challenge when dealing with highly heterogeneous data and it can sometimes be inadequate to adopt an approach where a single model is trained for usage at all nodes in the network. Different approaches have been investigated to succumb this issue such as adapting the trained model to each node and clustering the nodes in the network and train a different model for each cluster where the data is less heterogeneous. In this work we study the possibilities to improve the local model performance utilizing the hierarchical setup that comes with clustering the participating clients in the network. Experiments are carried out featuring a Long Short-Term Memory network to perform time series forecasting to evaluate different approaches utilizing the hierarchical setup and comparing them to standard federated learning approaches. The experiments are done using a dataset collected by Ericsson AB consisting of handovers recorded at base stations in an European city. The hierarchical approaches didn’t show any benefit over common two-level approaches.Federated Learning står inför en utmaning när det gäller att hantera data med en hög grad av heterogenitet och det kan i vissa fall vara olämpligt att använda sig av en approach där en och samma modell är tränad för att användas av alla noder i nätverket. Olika approacher för att hantera detta problem har undersökts som att anpassa den tränade modellen till varje nod och att klustra noderna i nätverket och träna en egen modell för varje kluster inom vilket datan är mindre heterogen. I detta arbete studeras möjligheterna att förbättra prestandan hos de lokala modellerna genom att dra nytta av den hierarkiska anordning som uppstår när de deltagande noderna i nätverket grupperas i kluster. Experiment är utförda med ett Long Short-Term Memory-nätverk för att utföra tidsserieprognoser för att utvärdera olika approacher som drar nytta av den hierarkiska anordningen och jämför dem med vanliga federated learning-approacher. Experimenten är utförda med ett dataset insamlat av Ericsson AB. Det består av "handoversfrån basstationer i en europeisk stad. De hierarkiska approacherna visade inga fördelar jämfört med de vanliga två-nivåapproacherna.
2
Taiello, Riccardo. "Apprentissage automatique sécurisé pour l'analyse collaborative des données de santé à grande échelle". Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ4031.
Texto completo da fonteResumo:
Cette thèse de doctorat explore l'intégration de la préservation de la confidentialité, de l'imagerie médicale et de l'apprentissage fédéré (FL) à l'aide de méthodes cryptographiques avancées. Dans le cadre de l'analyse d'images médicales, nous développons un cadre de recalage d'images préservant la confidentialité (PPIR). Ce cadre aborde le défi du recalage des images de manière confidentielle, sans révéler leur contenu. En étendant les paradigmes de recalage classiques, nous incorporons des outils cryptographiques tels que le calcul multipartite sécurisé et le chiffrement homomorphe pour effectuer ces opérations en toute sécurité. Ces outils sont essentiels car ils empêchent les fuites de données pendant le traitement. Étant donné les défis associés à la performance et à l'évolutivité des méthodes cryptographiques dans les données de haute dimension, nous optimisons nos opérations de recalage d'images en utilisant des approximations de gradient. Notre attention se porte sur des méthodes de recalage de plus en plus complexes, telles que les approches rigides, affines et non linéaires utilisant des splines cubiques ou des difféomorphismes, paramétrées par des champs de vitesses variables dans le temps. Nous démontrons comment ces méthodes de recalage sophistiquées peuvent intégrer des mécanismes de préservation de la confidentialité de manière efficace dans diverses tâches.Parallèlement, la thèse aborde le défi des retardataires dans l'apprentissage fédéré, en mettant l'accent sur le rôle de l'agrégation sécurisée (SA) dans l'entraînement collaboratif des modèles. Nous introduisons "Eagle", un schéma SA synchrone conçu pour optimiser la participation des dispositifs arrivant tardivement, améliorant ainsi considérablement les efficacités computationnelle et de communication. Nous présentons également "Owl", adapté aux environnements FL asynchrones tamponnés, surpassant constamment les solutions antérieures. En outre, dans le domaine de la Buffered AsyncSA, nous proposons deux nouvelles approches : "Buffalo" et "Buffalo+". "Buffalo" fait progresser les techniques de SA pour la Buffered AsyncSA, tandis que "Buffalo+" contrecarre les attaques sophistiquées que les méthodes traditionnelles ne parviennent pas à détecter. Cette solution exploite les propriétés des fonctions de hachage incrémentielles et explore la parcimonie dans la quantification des gradients locaux des modèles clients. "Buffalo" et "Buffalo+" sont validés théoriquement et expérimentalement, démontrant leur efficacité dans une nouvelle tâche de FL inter-dispositifs pour les dispositifs médicaux.Enfin, cette thèse a accordé une attention particulière à la traduction des outils de préservation de la confidentialité dans des applications réelles, notamment grâce au cadre open-source FL Fed-BioMed. Les contributions concernent l'introduction de l'une des premières implémentations pratiques de SA spécifiquement conçues pour le FL inter-silos entre hôpitaux, mettant en évidence plusieurs cas d'utilisation pratiquesThis PhD thesis explores the integration of privacy preservation, medical imaging, and Federated Learning (FL) using advanced cryptographic methods. Within the context of medical image analysis, we develop a privacy-preserving image registration (PPIR) framework. This framework addresses the challenge of registering images confidentially, without revealing their contents. By extending classical registration paradigms, we incorporate cryptographic tools like secure multi-party computation and homomorphic encryption to perform these operations securely. These tools are vital as they prevent data leakage during processing. Given the challenges associated with the performance and scalability of cryptographic methods in high-dimensional data, we optimize our image registration operations using gradient approximations. Our focus extends to increasingly complex registration methods, such as rigid, affine, and non-linear approaches using cubic splines or diffeomorphisms, parameterized by time-varying velocity fields. We demonstrate how these sophisticated registration methods can integrate privacy-preserving mechanisms effectively across various tasks. Concurrently, the thesis addresses the challenge of stragglers in FL, emphasizing the role of Secure Aggregation (SA) in collaborative model training. We introduce "Eagle", a synchronous SA scheme designed to optimize participation by late-arriving devices, significantly enhancing computational and communication efficiencies. We also present "Owl", tailored for buffered asynchronous FL settings, consistently outperforming earlier solutions. Furthermore, in the realm of Buffered AsyncSA, we propose two novel approaches: "Buffalo" and "Buffalo+". "Buffalo" advances SA techniques for Buffered AsyncSA, while "Buffalo+" counters sophisticated attacks that traditional methods fail to detect, such as model replacement. This solution leverages the properties of incremental hash functions and explores the sparsity in the quantization of local gradients from client models. Both Buffalo and Buffalo+ are validated theoretically and experimentally, demonstrating their effectiveness in a new cross-device FL task for medical devices.Finally, this thesis has devoted particular attention to the translation of privacy-preserving tools in real-world applications, notably through the FL open-source framework Fed-BioMed. Contributions concern the introduction of one of the first practical SA implementations specifically designed for cross-silo FL among hospitals, showcasing several practical use cases
3
Mäenpää, Dylan. "Towards Peer-to-Peer Federated Learning: Algorithms and Comparisons to Centralized Federated Learning". Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176778.
Texto completo da fonteResumo:
Due to privacy and regulatory reasons, sharing data between institutions can be difficult. Because of this, real-world data are not fully exploited by machine learning (ML). An emerging method is to train ML models with federated learning (FL) which enables clients to collaboratively train ML models without sharing raw training data. We explored peer-to-peer FL by extending a prominent centralized FL algorithm called Fedavg to function in a peer-to-peer setting. We named this extended algorithm FedavgP2P. Deep neural networks at 100 simulated clients were trained to recognize digits using FedavgP2P and the MNIST data set. Scenarios with IID and non-IID client data were studied. We compared FedavgP2P to Fedavg with respect to models' convergence behaviors and communication costs. Additionally, we analyzed the connection between local client computation, the number of neighbors each client communicates with, and how that affects performance. We also attempted to improve the FedavgP2P algorithm with heuristics based on client identities and per-class F1-scores. The findings showed that by using FedavgP2P, the mean model convergence behavior was comparable to a model trained with Fedavg. However, this came with a varying degree of variation in the 100 models' convergence behaviors and much greater communications costs (at least 14.9x more communication with FedavgP2P). By increasing the amount of local computation up to a certain level, communication costs could be saved. When the number of neighbors a client communicated with increased, it led to a lower variation of the models' convergence behaviors. The FedavgP2P heuristics did not show improved performance. In conclusion, the overall findings indicate that peer-to-peer FL is a promising approach.
4
Liang, Jiarong. "Federated Learning for Bioimage Classification". Thesis, Uppsala universitet, Institutionen för biologisk grundutbildning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-420615.
Texto completo da fonte
5
Zhao, Qiwei. "Federated Learning with Heterogeneous Challenge". Thesis, The University of Sydney, 2022. https://hdl.handle.net/2123/27399.
Texto completo da fonteResumo:
Federated learning allows the training of a model from the distributed data of many clients under the orchestration of a central server. With the increasing concern on privacy, federated learning draws great attention from both academia and industry. However, the heterogeneous challenges introduced by natural characters of federated learning settings significantly degrade the performance of federated learning methods. Specifically, these heterogeneous challenges include the heterogeneous data challenges and the heterogeneous scenario challenges.
Data heterogeneous challenges mean the significant differences between the datasets of numerous users. In federated learning, the data is stored separately on many distanced clients, causing these challenges. In addition, the heterogeneous scenario challenges refer to the differences between the devices participating in federated learning. Furthermore, the suitable models vary among the different scenarios. However, many existing federated learning methods use a single global model for all the devices' scenarios, which is not optimal for these two challenges.
We first propose a novel federated learning framework called local union in federated learning (LU-FL) to address these challenges. LU-FL incorporates the hierarchical knowledge distillation mechanism that effectively transfers knowledge among different models. So, LU-FL can enable any number of models to be used on each client. Allocating the specially designed models to different clients can mitigate the adverse effects caused by these challenges. At the same time, it can further improve the accuracy of the output models.
Extensive experimental results over several popular datasets demonstrate the effectiveness of our proposed method. It can effectively reduce the harmful effects of heterogeneous challenges, improving the accuracy of the final output models and the adaptability of the clients to various scenarios. So, it lets federated learning methods be applied in more diverse scenarios.
Keywords: federated learning, neural networks, knowledge distillation, computer vision
6
Carlsson, Robert. "Privacy-Preserved Federated Learning : A survey of applicable machine learning algorithms in a federated environment". Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-424383.
Texto completo da fonteResumo:
There is a potential in the field of medicine and finance of doing collaborative machine learning. These areas gather data which can be used for developing machine learning models that could predict all from sickness in patients to acts of economical crime like fraud. The problem that exists is that the data collected is mostly of confidential nature and should be handled with precaution. This makes the standard way of doing machine learning - gather data at one centralized server - unwanted to achieve. The safety of the data have to be taken into account. In this project we will explore the Federated learning approach of ”bringing the code to the data, instead of data to the code”. It is a decentralized way of doing machine learning where models are trained on connected devices and data is never shared. Keeping the data privacypreserved.
7
Dinh, The Canh. "Distributed Algorithms for Fast and Personalized Federated Learning". Thesis, The University of Sydney, 2023. https://hdl.handle.net/2123/30019.
Texto completo da fonteResumo:
The significant increase in the number of cutting-edge user equipment (UE) results in the phenomenal growth of the data volume generated at the edge. This shift fuels the booming trend of an emerging technique named Federated Learning. In contrast to traditional methods in which data is collected and processed centrally, FL builds a global model from contributions of UE's model without sending private data then effectively ensures data privacy. However, FL faces challenges in non-identically distributed (non-IID) data, communication cost, and convergence rate.
Firstly, we propose first-order optimization FL algorithms named FedApprox and FEDL to improve the convergence rate. We propose FedApprox exploiting proximal stochastic variance-reduced gradient methods and extract insights from convergence conditions via the algorithm’s parameter control. We then propose FEDL to handle heterogeneous UE data and characterize the trade-off between local computation and global communication. Experimentally, FedApprox outperforms vanilla FedAvg while FEDL outperforms FedApprox and FedAvg.
Secondly, we consider the communication between edges to be more costly than local computational overhead. We propose DONE, a distributed approximate Newton-type algorithm for communication-efficient federated edge learning. DONE approximates Newton direction using classical Richardson iteration on each edge. Experimentally, DONE attains a comparable performance to Newton’s method and outperforms first-order algorithms.
Finally, we address the non-IID issue by proposing pFedMe, a personalized FL algorithm using Moreau envelopes. pFedMe achieves quadratic speedup for strongly convex and sublinear speedup of order 2/3 for smooth nonconvex objectives. We then propose FedU, a Federated Multitask Learning algorithm using Laplacian regularization to leverage the relationships among the users' models. Experimentally, pFedMe excels FedAvg and Per-FedAvg while FedU outperforms pFedMe and MOCHA.
8
Felix, Johannes Morsbach. "Hardened Model Aggregation for Federated Learning backed by Distributed Trust Towards decentralizing Federated Learning using a Blockchain". Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-423621.
Texto completo da fonteResumo:
Federated learning enables the training of machine learning models on isolated data islands but also introduces new security challenges. Besides training-data-poisoning and model-update-poisoning, centralized federated learning systems are subject to a third type of poisoning attack: model-aggregation-poisoning. In this type of attack an adversary tampers with the model aggregation in order to bias the model. This can cause immense harm and severely weaken the trust a model-consumer puts into federatively trained models. This thesis proposes a hardened model aggregation scheme based on decentralization to close such attack vectors by design. It replaces the central aggregation server with a combination of decentralized computing and decentralized storage. A reference implementation based on the Ethereum platform and the Interplanetary File System (IPFS) is compared to a classic centralized federated learning system in terms of model performance, communication cost and resilience against said attacks. This thesis shows that such a decentralized federated learning system effectively eliminates model-aggregation-poisoning andtraining-disruption attacks at the cost of increased network traffic while achieving identical model performance.
9
Leconte, Louis. "Compression and federated learning : an approach to frugal machine learning". Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS107.
Texto completo da fonteResumo:
Les appareils et outils “intelligents” deviennent progressivement la norme, la mise en œuvre d'algorithmes basés sur des réseaux neuronaux artificiels se développant largement. Les réseaux neuronaux sont des modèles non linéaires d'apprentissage automatique avec de nombreux paramètres qui manipulent des objets de haute dimension et obtiennent des performances de pointe dans divers domaines, tels que la reconnaissance d'images, la reconnaissance vocale, le traitement du langage naturel et les systèmes de recommandation.Toutefois, l'entraînement d'un réseau neuronal sur un appareil à faible capacité de calcul est difficile en raison de problèmes de mémoire, de temps de calcul ou d'alimentation. Une approche naturelle pour simplifier cet entraînement consiste à utiliser des réseaux neuronaux quantifiés, dont les paramètres et les opérations utilisent des primitives efficaces à faible bit. Cependant, l'optimisation d'une fonction sur un ensemble discret en haute dimension est complexe et peut encore s'avérer prohibitive en termes de puissance de calcul. C'est pourquoi de nombreuses applications modernes utilisent un réseau d'appareils pour stocker des données individuelles et partager la charge de calcul. Une nouvelle approche a été proposée, l'apprentissage fédéré, qui prend en compte un environnement distribué : les données sont stockées sur des appareils différents et un serveur central orchestre le processus d'apprentissage sur les divers appareils.Dans cette thèse, nous étudions différents aspects de l'optimisation (stochastique) dans le but de réduire les coûts énergétiques pour des appareils potentiellement très hétérogènes. Les deux premières contributions de ce travail sont consacrées au cas des réseaux neuronaux quantifiés. Notre première idée est basée sur une stratégie de recuit : nous formulons le problème d'optimisation discret comme un problème d'optimisation sous contraintes (où la taille de la contrainte est réduite au fil des itérations). Nous nous sommes ensuite concentrés sur une heuristique pour la formation de réseaux neuronaux profonds binaires. Dans ce cadre particulier, les paramètres des réseaux neuronaux ne peuvent avoir que deux valeurs. Le reste de la thèse s'est concentré sur l'apprentissage fédéré efficace. Suite à nos contributions développées pour l'apprentissage de réseaux neuronaux quantifiés, nous les avons intégrées dans un environnement fédéré. Ensuite, nous avons proposé une nouvelle technique de compression sans biais qui peut être utilisée dans n'importe quel cadre d'optimisation distribuée basé sur le gradient. Nos dernières contributions abordent le cas particulier de l'apprentissage fédéré asynchrone, où les appareils ont des vitesses de calcul et/ou un accès à la bande passante différents. Nous avons d'abord proposé une contribution qui repondère les contributions des dispositifs distribués. Dans notre travail final, à travers une analyse détaillée de la dynamique des files d'attente, nous proposons une amélioration significative des bornes de complexité fournies dans la littérature sur l'apprentissage fédéré asynchrone.En résumé, cette thèse présente de nouvelles contributions au domaine des réseaux neuronaux quantifiés et de l'apprentissage fédéré en abordant des défis critiques et en fournissant des solutions innovantes pour un apprentissage efficace et durable dans un environnement distribué et hétérogène. Bien que les avantages potentiels soient prometteurs, notamment en termes d'économies d'énergie, il convient d'être prudent car un effet rebond pourrait se produire“Intelligent” devices and tools are gradually becoming the standard, as the implementation of algorithms based on artificial neural networks is experiencing widespread development. Neural networks consist of non-linear machine learning models that manipulate high-dimensional objects and obtain state-of-the-art performances in various areas, such as image recognition, speech recognition, natural language processing, and recommendation systems.However, training a neural network on a device with lower computing capacity can be challenging, as it can imply cutting back on memory, computing time or power. A natural approach to simplify this training is to use quantized neural networks, whose parameters and operations use efficient low-bit primitives. However, optimizing a function over a discrete set in high dimension is complex, and can still be prohibitively expensive in terms of computational power. For this reason, many modern applications use a network of devices to store individual data and share the computational load. A new approach, federated learning, considers a distributed environment: Data is stored on devices and a centralized server orchestrates the training process across multiple devices.In this thesis, we investigate different aspects of (stochastic) optimization with the goal of reducing energy costs for potentially very heterogeneous devices. The first two contributions of this work are dedicated to the case of quantized neural networks. Our first idea is based on an annealing strategy: we formulate the discrete optimization problem as a constrained optimization problem (where the size of the constraint is reduced over iterations). We then focus on a heuristic for training binary deep neural networks. In this particular framework, the parameters of the neural networks can only have two values. The rest of the thesis is about efficient federated learning. Following our contributions developed for training quantized neural network, we integrate them into a federated environment. Then, we propose a novel unbiased compression technique that can be used in any gradient based distributed optimization framework. Our final contributions address the particular case of asynchronous federated learning, where devices have different computational speeds and/or access to bandwidth. We first propose a contribution that reweights the contributions of distributed devices. Then, in our final work, through a detailed queuing dynamics analysis, we propose a significant improvement to the complexity bounds provided in the literature onasynchronous federated learning.In summary, this thesis presents novel contributions to the field of quantized neural networks and federated learning by addressing critical challenges and providing innovative solutions for efficient and sustainable learning in a distributed and heterogeneous environment. Although the potential benefits are promising, especially in terms of energy savings, caution is needed as a rebound effect could occur
10
Adapa, Supriya. "TensorFlow Federated Learning: Application to Decentralized Data". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Encontre o texto completo da fonteResumo:
Machine learning is a complex discipline. But implementing machine learning models is far less daunting and difficult than it used to be, thanks to machine learning frameworks such as Google’s TensorFlow Federated that ease the process of acquiring data, training models, serving predictions, and refining future results. There are an estimated 3 billion smartphones in the world and 7 billion connected devices. These phones and devices are constantly generating new data. Traditional analytics and machine learning need that data to be centrally collected before it is processed to yield insights, ML models, and ultimately better products. This centralized approach can be problematic if the data is sensitive or expensive to centralize. Wouldn’t it be better if we could run the data analysis and machine learning right on the devices where that data is generated, and still be able to aggregate together what’s been learned? TensorFlow Federated (TFF) is an open-source framework for experimenting with machine learning and other computations on decentralized data. It implements an approach called Federated Learning (FL), which enables many participating clients to train shared ML models while keeping their data locally. We have designed TFF based on our experiences with developing the federated learning technology at Google, where it powers ML models for mobile keyboard predictions and on-device search. With TFF, we are excited to put a flexible, open framework for locally simulating decentralized computations into the hands of all TensorFlow users. By using Twitter datasets we have done text classification of positives and negatives tweets of Twitter Account by using the Twitter application in machine learning.
11
Kim, Yeongwoo. "Dynamic GAN-based Clustering in Federated Learning". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285576.
Texto completo da fonteResumo:
As the era of Industry 4.0 arises, the number of devices that are connectedto a network has increased. The devices continuously generate data that hasvarious information from power consumption to the configuration of thedevices. Since the data have the raw information about each local node inthe network, the manipulation of the information brings a potential to benefitthe network with different methods. However, due to the large amount ofnon-IID data generated in each node, manual operations to process the dataand tune the methods became challenging. To overcome the challenge, therehave been attempts to apply automated methods to build accurate machinelearning models by a subset of collected data or cluster network nodes byleveraging clustering algorithms and using machine learning models withineach cluster. However, the conventional clustering algorithms are imperfectin a distributed and dynamic network due to risk of data privacy, the nondynamicclusters, and the fixed number of clusters. These limitations ofthe clustering algorithms degrade the performance of the machine learningmodels because the clusters may become obsolete over time. Therefore, thisthesis proposes a three-phase clustering algorithm in dynamic environmentsby leveraging 1) GAN-based clustering, 2) cluster calibration, and 3) divisiveclustering in federated learning. GAN-based clustering preserves data becauseit eliminates the necessity of sharing raw data in a network to create clusters.Cluster calibration adds dynamics to fixed clusters by continuously updatingclusters and benefits methods that manage the network. Moreover, the divisiveclustering explores the different number of clusters by iteratively selectingand dividing a cluster into multiple clusters. As a result, we create clustersfor dynamic environments and improve the performance of machine learningmodels within each cluster.ett nätverk ökat. Enheterna genererar kontinuerligt data som har varierandeinformation, från strömförbrukning till konfigurationen av enheterna. Eftersomdatan innehåller den råa informationen om varje lokal nod i nätverket germanipulation av informationen potential att gynna nätverket med olika metoder.På grund av den stora mängden data, och dess egenskap av att vara icke-o.l.f.,som genereras i varje nod blir manuella operationer för att bearbeta data ochjustera metoderna utmanande. För att hantera utmaningen finns försök med attanvända automatiserade metoder för att bygga precisa maskininlärningsmodellermed hjälp av en mindre mängd insamlad data eller att gruppera nodergenom att utnyttja klustringsalgoritmer och använda maskininlärningsmodellerinom varje kluster. De konventionella klustringsalgoritmerna är emellertidofullkomliga i ett distribuerat och dynamiskt nätverk på grund av risken fördataskydd, de icke-dynamiska klusterna och det fasta antalet kluster. Dessabegränsningar av klustringsalgoritmerna försämrar maskininlärningsmodellernasprestanda eftersom klustren kan bli föråldrade med tiden. Därför föreslårdenna avhandling en trefasklustringsalgoritm i dynamiska miljöer genom attutnyttja 1) GAN-baserad klustring, 2) klusterkalibrering och 3) klyvning avkluster i federerad inlärning. GAN-baserade klustring bevarar dataintegriteteneftersom det eliminerar behovet av att dela rådata i ett nätverk för att skapakluster. Klusterkalibrering lägger till dynamik i klustringen genom att kontinuerligtuppdatera kluster och fördelar metoder som hanterar nätverket. Dessutomdelar den klövlande klustringen olika antal kluster genom att iterativt välja ochdela ett kluster i flera kluster. Som ett resultat skapar vi kluster för dynamiskamiljöer och förbättrar prestandan hos maskininlärningsmodeller inom varjekluster.
12
Pekkanen, Linus, e Patrik Johansson. "Simulating Broadband Analog Aggregation for Federated Learning". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-295616.
Texto completo da fonteResumo:
With increasing amounts of data coming fromconnecting progressively more devices, new machine learningmodels have risen. For wireless networks the idea of using adistributed approach to machine learning has gained increasingpopularity, where all nodes in the network participate in creatinga global machine learning model by training with the localdata stored at each node, an example of this approach is calledfederated learning. However, traditional communication protocolshave been proven inefficient. This opens up opportunities todesign new machine-learning specific communication schemes.The concept ofOver-the-air computationis built on the fact thata wireless communication channel can naturally compute somelinear functions, for instance the sum. If all nodes in a networktransmits simultaneously to a server, the signals are aggregatedbefore reaching the server.I takt med denökande datamängden frånallt fler uppkopplade enheter har nya modeller för mask-ininlärning dykt upp. För trådlösa nätverk har idén att appliceradecentraliserade maskininlärnings modellerökat i popularitet,där alla noder i nätverket bidrar till en global maskininlärningsmodell genom att träna på den data som finns lokalt på varjenod. Ett exempel på en sådan metodärFederated Learning.Traditionella metoder för kommunikation har visat sig varaineffektiva vilket öppnar upp möjligheten för att designa nyamaskininlärningsspecifika kommunikationsscheman. Konceptetover-the-air computationutnyttjar det faktum att en trådlöskommunikationskanal naturligt kan beräkna vissa funktioner,som exempelvis en summa. Om alla noder i nätverket sändertill en server samtidigt aggregeras signalerna genom interferensinnan de når servern.
Kandidatexjobb i elektroteknik 2020, KTH, Stockholm
13
Alotaibi, Abdulrahman. "Wisdom of the machines : federated learning using OPAL". Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/120686.
Texto completo da fonteResumo:
Thesis: S.M., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2018.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 67-68).
Wisdom of the crowds (WOC) is an old concept that started by recording and aggregating people's estimations. It is one of the useful tools that exists today and allows many estimation applications to work correctly. Moreover, Open algorithms (OPAL) is a useful platform that enables institutions and individuals to share sensitive data, and increases the privacy of the data. In addition, federated learning is a new way to build and generate machine learning models by aggregating their hyperparameters. In this thesis, I show how to combine the three different concepts to build machine learning models on top of OPAL that utilize federated learning on a network. I then extend OPAL to support this new feature and demonstrate how to build a machine learning model using small independent models.
by Abdulrahman Alotaibi.
S.M.
14
Konečný, Jakub. "Stochastic, distributed and federated optimization for machine learning". Thesis, University of Edinburgh, 2017. http://hdl.handle.net/1842/31478.
Texto completo da fonteResumo:
We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of stochastic gradient descent with a variance reduction property that enables linear convergence for strongly convex objectives. Second, we study distributed setting, in which the data describing the optimization problem does not fit into a single computing node. In this case, traditional methods are inefficient, as the communication costs inherent in distributed optimization become the bottleneck. We propose a communication-efficient framework which iteratively forms local subproblems that can be solved with arbitrary local optimization algorithms. Finally, we introduce the concept of Federated Optimization/Learning, where we try to solve the machine learning problems without having data stored in any centralized manner. The main motivation comes from industry when handling user-generated data. The current prevalent practice is that companies collect vast amounts of user data and store them in datacenters. An alternative we propose is not to collect the data in first place, and instead occasionally use the computational power of users' devices to solve the very same optimization problems, while alleviating privacy concerns at the same time. In such setting, minimization of communication rounds is the primary goal, and we demonstrate that solving the optimization problems in such circumstances is conceptually tractable.
15
Sani, Lorenzo. "Unsupervised clustering of MDS data using federated learning". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022. http://amslaurea.unibo.it/25591/.
Texto completo da fonteResumo:
In this master thesis we developed a model for unsupervised clustering on a data set of biomedical data. This data has been collected by GenoMed4All consortium from patients affected by Myelodysplastic Syndrome (MDS), that is an haematological disease. The main focus is put on the genetic mutations collected that are used as features of the patients in order to cluster them. Clustering approaches have been used in several studies concerning haematological diseases such MDS. A neural network-based model was used to solve the task. The results of the clustering have been compared with labels from a "gold standard'' technique, i.e. hierarchical Dirichlet processes (HDP). Our model was designed to be also implemented in the context of federated learning (FL). This innovative technique is able to achieve machine learning objective without the necessity of collecting all the data in one single center, allowing strict privacy policies to be respected. Federated learning was used because of its properties, and because of the sensitivity of data. Several recent studies regarding clinical problems addressed with machine learning endorse the development of federated learning settings in such context, because its privacy preserving properties could represent a cornerstone for applying machine learning techniques to medical data. In this work will be then discussed the clustering performance of the model, and also its generative capabilities.
16
Smith, Arthur M. D. "A Study on Federated Learning Systems in Healthcare". Youngstown State University / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1629188090536169.
Texto completo da fonte
17
Lundberg, Oskar. "Decentralized machine learning on massive heterogeneous datasets : A thesis about vertical federated learning". Thesis, Uppsala universitet, Avdelningen för systemteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-444639.
Texto completo da fonteResumo:
The need for a method to create a collaborative machine learning model which can utilize data from different clients, each with privacy constraints, has recently emerged. This is due to privacy restrictions, such as General Data Protection Regulation, together with the fact that machine learning models in general needs large size data to perform well. Google introduced federated learning in 2016 with the aim to address this problem. Federated learning can further be divided into horizontal and vertical federated learning, depending on how the data is structured at the different clients. Vertical federated learning is applicable when many different features is obtained on distributed computation nodes, where they can not be shared in between. The aim of this thesis is to identify the current state of the art methods in vertical federated learning, implement the most interesting ones and compare the results in order to draw conclusions of the benefits and drawbacks of the different methods. From the results of the experiments, a method called FedBCD shows very promising results where it achieves massive improvements in the number of communication rounds needed for convergence, at the cost of more computations at the clients. A comparison between synchronous and asynchronous approaches shows slightly better results for the synchronous approach in scenarios with no delay. Delay refers to slower performance in one of the workers, either due to lower computational resources or due to communication issues. In scenarios where an artificial delay is implemented, the asynchronous approach shows superior results due to its ability to continue training in the case of delays in one or several of the clients.
18
Vikström, Johan. "Comparing decentralized learning to Federated Learning when training Deep Neural Networks under churn". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-300391.
Texto completo da fonteResumo:
Decentralized Machine Learning could address some problematic facets with Federated Learning. There is no central server acting as an arbiter of whom or what may benefit from Machine Learning models created by the vast amount of data becoming available in recent years. It could also increase the reliability and scalability of Machine Learning systems thereby drawing the benefit of having more data accessible. Gossip Learning is such a protocol, but has primarily been designed with linear models in mind. How does Gossip Learning perform when training Deep Neural Networks? Could it be a viable alternative to Federated Learning? In this thesis, we implement Gossip Learning using two different model merging strategies. We also design and implement two extensions to this protocol with the goal of achieving higher performance when training under churn. The training methods are compared on two tasks: image classification on the Federated Extended MNIST dataset and time- series forecasting on the NN5 dataset. Additionally, we also run an experiment where learners churn, alternating between being available and unavailable. We find that Gossip Learning performs slightly better in settings where learners do not churn but is vastly outperformed in the setting where they do.Decentraliserad Maskinginlärning kan lösa några problematiska aspekter med Federated Learning. Det finns ingen central server som agerar som domare för vilka som får gagna av Maskininlärningsmodellerna skapad av den stora mäng data som blivit tillgänglig på senare år. Det skulle också kunna öka pålitligheten och skalbarheten av Maskininlärningssystem och därav dra nytta av att mer data är tillgänglig. Gossip Learning är ett sånt protokoll, men det är primärt designat med linjära modeller i åtanke. Hur presterar Gossip Learning när man tränar Djupa Neurala Nätverk? Kan det vara ett möjligt alternativ till Federated Learning? I det här exjobbet implementerar vi Gossip Learning med två olika modelsammanslagningstekniker. Vi designar och implementerar även två tillägg till protokollet med målet att uppnå bättre prestanda när man tränar i system där noder går ner och kommer up. Träningsmetoderna jämförs på två uppgifter: bildklassificering på Federated Extended MNIST datauppsättningen och tidsserieprognostisering på NN5 datauppsättningen. Dessutom har vi även experiment då noder alternerar mellan att vara tillgängliga och otillgängliga. Vi finner att Gossip Learning presterar marginellt bättre i miljöer då noder alltid är tillgängliga men är kraftigt överträffade i miljöer då noder alternerar mellan att vara tillgängliga och otillgängliga.
19
Liverani, Tommaso. "Federated Learning per Applicazioni Edge Cloud su Piattaforma fog05". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Encontre o texto completo da fonteResumo:
Federated learning è sicuramente una delle tecniche di machine learning di maggiore interesse attualmente.
Esso trova applicazione nello scenario fog computing in cui risulta spesso necessario mantenere la riservatezza dei dati mantenuti nei nodi fog.
La riservatezza dei dati è infatti una delle caratteristiche peculiari dei processi di federated learning.
In tali scenari risulta particolarmente utile impiegare una piattaforma con supporto alla migrazione che potrà essere utilizzato per implementare determinati meccanismi come il bilanciamento di carico.
Questo supporto potrà quindi essere impiegato per la migrazione di entità coinvolte tra nodi fog in un'architettura edge-cloud o per abilitare futuri scenari completamente decentralizzati.
L'obiettivo della tesi è quindi la realizzazione di un'applicazione per federated learning con supporto alla migrazione per architetture edge-cloud.
A tale scopo si è scelto di utilizzare fog05.
Fog05 è una piattaforma per fog computing con supporto alla migrazione che presenta caratteristiche particolarmente innovative e interessanti rispetto alle soluzioni attualmente diffuse.
Fog05 permette la gestione di sistemi estremamente eterogenei attraverso l’utilizzo di plugin che le consentono di interagire con tecnologie differenti come lxd,docker e kvm.
In una prima fase abbiamo quindi realizzato l’applicazione descritta tramite fog05 mentre in una seconda fase abbiamo studiato e testato il supporto alla migrazione di fog05 rispetto alle tecnologie supportate.
20
Garcia, Bernal Daniel. "Decentralizing Large-Scale Natural Language Processing with Federated Learning". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-278822.
Texto completo da fonteResumo:
Natural Language Processing (NLP) is one of the most popular and visible forms of Artificial Intelligence in recent years. This is partly because it has to do with a common characteristic of human beings: language. NLP applications allow to create new services in the industrial sector in order to offer new solutions and provide significant productivity gains. All of this has happened thanks to the rapid progression of Deep Learning models. Large scale contextual representation models, such asWord2Vec, ELMo and BERT, have significantly advanced NLP in recently years. With these latest NLP models, it is possible to understand the semantics of text to a degree never seen before. However, they require large amounts of text data to process to achieve high-quality results. This data can be gathered from different sources, but one of the main collection points are devices such as smartphones, smart appliances and smart sensors. Lamentably, joining and accessing all this data from multiple sources is extremely challenging due to privacy and regulatory reasons. New protocols and techniques have been developed to solve this limitation by training models in a massively distributed manner taking advantage of the powerful characteristic of the devices that generates the data. Particularly, this research aims to test the viability of training NLP models, in specific Word2Vec, with a massively distributed protocol like Federated Learning. The results show that FederatedWord2Vecworks as good as Word2Vec is most of the scenarios, even surpassing it in some semantics benchmark tasks. It is a novel area of research, where few studies have been conducted, with a large knowledge gap to fill in future researches.Naturlig språkbehandling är en av de mest populära och synliga formerna av artificiell intelligens under de senaste åren. Det beror delvis på att det har att göra med en gemensam egenskap hos människor: språk. Naturlig språkbehandling applikationer gör det möjligt att skapa nya tjänster inom industrisektorn för att erbjuda nya lösningar och ge betydande produktivitetsvinster. Allt detta har hänt tack vare den snabba utvecklingen av modeller för djup inlärning. Modeller i storskaligt sammanhang, som Word2Vec, ELMo och BERT har väsentligt avancerat naturligt språkbehandling på senare tid år. Med dessa senaste naturliga språkbearbetningsmo modeller är det möjligt att förstå textens semantik i en grad som aldrig sett förut. De kräver dock stora mängder textdata för att bearbeta för att uppnå högkvalitativa resultat. Denna information kan samlas in från olika källor, men ett av de viktigaste insamlingsställena är enheter som smartphones, smarta apparater och smarta sensorer. Beklagligtvis är det extremt utmanande att gå med och komma åt alla dessa uppgifter från flera källor på grund av integritetsskäl och regleringsskäl. Nya protokoll och tekniker har utvecklats för att lösa denna begränsning genom att träna modeller på ett massivt distribuerat sätt med fördel av de kraftfulla egenskaperna hos enheterna som genererar data. Särskilt syftar denna forskning till att testa livskraften för att utbilda naturligt språkbehandling modeller, i specifika Word2Vec, med ett massivt distribuerat protokoll som Förenat Lärande. Resultaten visar att det Förenade Word2Vec fungerar lika bra som Word2Vec är de flesta av scenarierna, till och med överträffar det i vissa semantiska riktmärken. Det är ett nytt forskningsområde, där få studier har genomförts, med ett stort kunskapsgap för att fylla i framtida forskningar.
21
Cetin, Burak. "Wireless Network Intrusion Detection and Analysis using Federated Learning". Youngstown State University / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1588778320687729.
Texto completo da fonte
22
Li, Yuntao. "Federated Learning for Time Series Forecasting Using Hybrid Model". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254677.
Texto completo da fonteResumo:
Time Series data has become ubiquitous thanks to affordable edge devices and sensors. Much of this data is valuable for decision making. In order to use these data for the forecasting task, the conventional centralized approach has shown deficiencies regarding large data communication and data privacy issues. Furthermore, Neural Network models cannot make use of the extra information from the time series, thus they usually fail to provide time series specific results. Both issues expose a challenge to large-scale Time Series Forecasting with Neural Network models. All these limitations lead to our research question:Can we realize decentralized time series forecasting with a Federated Learning mechanism that is comparable to the conventional centralized setup in forecasting performance?In this work, we propose a Federated Series Forecasting framework, resolving the challenge by allowing users to keep the data locally, and learns a shared model by aggregating locally computed updates. Besides, we design a hybrid model to enable Neural Network models utilizing the extra information from the time series to achieve a time series specific learning. In particular, the proposed hybrid outperforms state-of-art baseline data-central models with NN5 and Ericsson KPI data. Meanwhile, the federated settings of purposed model yields comparable results to data-central settings on both NN5 and Ericsson KPI data. These results together answer the research question of this thesis.Tidseriedata har blivit allmänt förekommande tack vare överkomliga kantenheter och sensorer. Mycket av denna data är värdefull för beslutsfattande. För att kunna använda datan för prognosuppgifter har den konventionella centraliserade metoden visat brister avseende storskalig datakommunikation och integritetsfrågor. Vidare har neurala nätverksmodeller inte klarat av att utnyttja den extra informationen från tidsserierna, vilket leder till misslyckanden med att ge specifikt tidsserierelaterade resultat. Båda frågorna exponerar en utmaning för storskalig tidsserieprognostisering med neurala nätverksmodeller. Alla dessa begränsningar leder till vår forskningsfråga:Kan vi realisera decentraliserad tidsserieprognostisering med en federerad lärningsmekanism som presterar jämförbart med konventionella centrala lösningar i prognostisering?I det här arbetet föreslår vi ett ramverk för federerad tidsserieprognos som löser utmaningen genom att låta användaren behålla data lokalt och lära sig en delad modell genom att aggregera lokalt beräknade uppdateringar. Dessutom utformar vi en hybrid modell för att möjliggöra neurala nätverksmodeller som kan utnyttja den extra informationen från tidsserierna för att uppnå inlärning av specifika tidsserier. Den föreslagna hybrida modellen presterar bättre än state-of-art centraliserade grundläggande modeller med NN5och Ericsson KPIdata. Samtidigt ger den federerade ansatsen jämförbara resultat med de datacentrala ansatserna för både NN5och Ericsson KPI-data. Dessa resultat svarar tillsammans på forskningsfrågan av denna avhandling.
23
Lavaur, Léo. "Improving intrusion detection in distributed systems with federated learning". Electronic Thesis or Diss., Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2024. http://www.theses.fr/2024IMTA0423.
Texto completo da fonteResumo:
La collaboration entre les différents acteurs de la cybersécurité est essentielle pour lutter contre des attaques de plus en plus nombreuses et sophistiquées. Pourtant, les organisations sont souvent réticentes à partager leurs données, par peur de compromettre leur confidentialité ou leur avantage concurrentiel, et ce même si cela pourrait améliorer leurs modèles de détection d’intrusions. L’apprentissage fédéré est un paradigme récent en apprentissage automatique qui permet à des clients répartis d’entraîner un modèle commun sans partager leurs données. Ces propriétés de collaboration et de confidentialité en font un candidat idéal pour des applications sensibles comme la détection d’intrusions. Si un certain nombre d’applications ont montré qu’il est, en effet, possible d’entraîner un modèle unique sur des données réparties de détection d’intrusions, peu se sont intéressées à l’aspect collaboratif de ce paradigme. Dans ce manuscrit, nous étudions l’utilisation de l’apprentissage fédéré pour construire des systèmes collaboratifs de détection d’intrusions. En particulier, nous explorons(i) l’impact de la qualité des données dans des contextes hétérogènes, (ii) l’exposition à certains types d’attaques par empoisonnement,et (iii) des outils et des méthodologies pour améliorer l’évaluation de ce type d’algorithmesCollaboration between different cybersecurity actors is essential to fight against increasingly sophisticated and numerous attacks. However, stakeholders are often reluctant to share their data, fearing confidentiality and privacy issues and the loss of their competitive advantage, although it would improve their intrusion detection models. Federated learning is a recent paradigm in machine learning that allows distributed clients to train a common model without sharing their data. These properties of collaboration and confidentiality make it an ideal candidate for sensitive applications such as intrusion detection. While several applications have shown that it is indeed possible to train a single model on distributed intrusion detection data, few have focused on the collaborative aspect of this paradigm. In this manuscript, we study the use of federated learning to build collaborative intrusion detection systems. In particular, we explore (i) the impact of data quality in heterogeneous contexts, (ii) the exposure to certain types of poisoning attacks, and (iii) tools and methodologies to improve the evaluation of these types of algorithms
24
Feraudo, Angelo. "Distributed Federated Learning in Manufacturer Usage Description (MUD) Deployment Environments". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Encontre o texto completo da fonteResumo:
Il costante avanzamento dei dispositivi Internet of Things (IoT) in diversi ambienti, ha provocato la necessità di nuovi meccanismi di sicurezza e monitoraggio in una rete. Tali dispositvi sono spesso considerati fonti di vulnerabilità sfruttabili da malintenzionati per accedere alla rete o condurre altri attacchi. Questo è dovuto alla natura stessa dei dispositivi, ovvero offrire servizi aventi a che fare con dati sensibili (p.es. videocamere) seppur con risorse molto limitate. Una soluzione in questa direzione, è l'impiego della specifica Manufacturer Usage Description (MUD), che impone al maufacturer dei dispositivi di fornire dei file contenenti un particolare pattern di comunicazione che i dispositivi da lui prodotti dovranno adottare. Tuttavia, tale specifica riduce solo parzialmente le suddette vulnerabilità. Infatti, diventa inverosimile definire un pattern di comunicazione per dispositivi IoT aventi un traffico di rete molto generico (p.es. Alexa). Perciò, è di grande interesse studiare un sistema di anomaly detection basato su tecniche di machine learning, che riesca a colmare tali vulnerabilità.
In questo lavoro, verranno esplorate tre prototipi di implementazione della specifica MUD, che si concluderà con la scelta di una tra queste. Successivamente, verrà prodotta una Proof-of-Concept uniforme a tale specifica, contenente un'ulteriore entità in grado di fornire maggiore autorità all'amministratore di rete in quest'ambiente. In una seconda fase, verrà analizzata un'architettura distribuita che riesca ad effettuare learning di anomalie direttamente sui dispositivi sfruttando il concetto di Federated Learning, il che significa garantire la privacy dei dati. L'idea fondamentale di questo lavoro è quindi quella di proporre un'architettura basata su queste due nuove tecnologie, in grado di ridurre al minimo vulnerabilità proprie dei dispositivi IoT in un ambiente distribuito garantendo il più possibile la privacy dei dati.
25
Backstad, Sebastian. "Federated Averaging Deep Q-NetworkA Distributed Deep Reinforcement Learning Algorithm". Thesis, Umeå universitet, Institutionen för datavetenskap, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-149637.
Texto completo da fonteResumo:
In the telecom sector, there is a huge amount of rich data generated every day. This trend will increase with the launch of 5G networks. Telco companies are interested in analyzing their data to shape and improve their core businesses. However, there can be a number of limiting factors that prevents them from logging data to central data centers for analysis. Some examples include data privacy, data transfer, network latency etc. In this work, we present a distributed Deep Reinforcement Learning (DRL) method called Federated Averaging Deep Q-Network (FADQN), that employs a distributed hierarchical reinforcement learning architecture. It utilizes gradient averaging to decrease communication cost. Privacy concerns are also satisfied by training the agent locally and only sending aggregated information to the centralized server. We introduce two versions of FADQN: synchronous and asynchronous. Results on the cart-pole environment show 80 times reduction in communication without any significant loss in performance. Additionally, in case of asynchronous approach, we see a great improvement in convergence.
26
Basnayake, Mudiyanselage V. (Vishaka). "Federated learning for enhanced sensor reliability of automated wireless networks". Master's thesis, University of Oulu, 2019. http://jultika.oulu.fi/Record/nbnfioulu-201908142761.
Texto completo da fonteResumo:
Abstract. Autonomous mobile robots working in-proximity humans and objects are becoming frequent and thus, avoiding collisions becomes important to increase the safety of the working environment. This thesis develops a mechanism to improve the reliability of sensor measurements in a mobile robot network taking into the account of inter-robot communication and costs of faulty sensor replacements. In this view, first, we develop a sensor fault prediction method utilizing sensor characteristics. Then, network-wide cost capturing sensor replacements and wireless communication is minimized subject to a sensor measurement reliability constraint. Tools from convex optimization are used to develop an algorithm that yields the optimal sensor selection and wireless information communication policy for aforementioned problem. Under the absence of prior knowledge on sensor characteristics, we utilize observations of sensor failures to estimate their characteristics in a distributed manner using federated learning. Finally, extensive simulations are carried out to highlight the performance of the proposed mechanism compared to several state-of-the-art methods.
27
Bagheri, Behrad. "Decentralized Federated Autonomous Organizations for Prognostics and Health Management". University of Cincinnati / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592133991337126.
Texto completo da fonte
28
Langelaar, Johannes, e Mattsson Adam Strömme. "Federated Neural Collaborative Filtering for privacy-preserving recommender systems". Thesis, Uppsala universitet, Avdelningen för systemteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-446913.
Texto completo da fonteResumo:
In this thesis a number of models for recommender systems are explored, all using collaborative filtering to produce their recommendations. Extra focus is put on two models: Matrix Factorization, which is a linear model and Multi-Layer Perceptron, which is a non-linear model. With an additional purpose of training the models without collecting any sensitive data from the users, both models were implemented with a learning technique that does not require the server's knowledge of the users' data, called federated learning. The federated version of Matrix Factorization is already well-researched, and has proven not to protect the users' data at all; the data is derivable from the information that the users communicate to the server that is necessary for the learning of the model. However, on the federated Multi-Layer Perceptron model, no research could be found. In this thesis, such a model is therefore designed and presented. Arguments are put forth in support of the privacy preservability of the model, along with a proof of the user data not being analytically derivable for the central server. In addition, new ways to further put the protection of the users' data on the test are discussed. All models are evaluated on two different data sets. The first data set contains data on ratings of movies and is called MovieLens 1M. The second is a data set that consists of anonymized fund transactions, provided by the Swedish bank SEB for this thesis. Test results suggest that the federated versions of the models can achieve similar recommendation performance as their non-federated counterparts.
29
Lu, Zonghao. "A case study about different network architectures in Federated Machine Learning". Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-425193.
Texto completo da fonteResumo:
Modern artificial intelligence (AI) technology is developing rapidly in recent years. Data is an important factor driving the development of AI.With the development of mobile Internet, more and more data is generated in different fields every day along with data sensitivity issues. As asignificant part of personal privacy, personal data must be respected and protected. Federated learning (FL) is a machine learning technology that can protect privacy because it keeps everyone’s data local. Many types of research have already confirmed that the bottleneck of federated learning is the communication between the client and servers. Different ways of communication methods have various characteristics, resulting in differences inefficiency. We present a benchmark for our FL system using HTTP and gRPC communication protocol respectively to show that gRPC framework is faster and has better scalability than HTTP protocol mainly because of the different architectures and way of compacting message of these two different communication protocols. In addition, we found that the system may get crashed when the loads increased. A registration mechanism is proposed to deal with the problem of insufficient computing resources and apply a new model updatestrategy to make the training process finish in a shorter time.Tryckt av:
30
Knight-Williams, Alex. "Time to Next Flow Classification in Mobile Networks with Federated Learning". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-287183.
Texto completo da fonteResumo:
Understanding traffic dynamics and user demand in a cellular network is essential for effective resource management, which in turn improves the network’s energy and cost efficiency. This thesis focuses on the task of classifying the time until the arrival of the next flow at a user level in a real network traffic data set. A range of machine learning and deep learning techniques are applied to this task, some of which are incorporated into a federated learning framework that ensures data privacy. The results demonstrate that the long short-term memory (LSTM) performs best on this task, although good performance can also be achieved with models of lower complexity. Furthermore, models developed through federated learning achieve comparable performance to those trained on centralised data.Att förstå trafikdynamik i ett cellulärt nätverk är fundamentalt för effektiv resurshantering, vilket förbättrar nätverkets energi- och kostnadseffektivitet. Denna uppsats fokuserar på att klassificera ankomsttid för nästa flöde på användarnivå i ett dataset innehållande nätverkstrafik från en operatör. En uppsättning maskininlärnings- och djupinlärningstekniker har applicerats, varav några har inkorporerats i ett ramverk för federerad inlärning som säkerställer användares dataintegritet. Resultaten visar att ett long short-term memory (LSTM) presterar bäst på denna uppgift, även om bra prestanda även kan uppnås med modeller av lägre komplexitet. Vidare så har modeller som tränats med hjälp av federerad inlärning jämförbar prestanda med de tränade på centraliserat data.
31
Mestoukirdi, Mohamad. "Reliable and Communication-Efficient Federated Learning for Future Intelligent Edge Networks". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS432.
Texto completo da fonteResumo:
Dans le domaine des futurs réseaux sans fil 6G, l'intégration de la périphérie intelligente grâce à l'avènement de l'IA représente un bond en avant considérable, promettant des avancées révolutionnaires en matière de communication sans fil. Cette intégration favorise une synergie harmonieuse, capitalisant sur le potentiel collectif de ces technologies transformatrices. Au cœur de cette intégration se trouve le rôle de l'apprentissage fédéré, un paradigme d'apprentissage décentralisé qui préserve la confidentialité des données tout en exploitant l'intelligence collective des appareils interconnectés. Dans la première partie de la thèse, nous nous attaquons au problème de l'hétérogénéité statistique dans l'apprentissage fédéré, qui découle des distributions de données divergentes entre les ensembles de données des dispositifs. Plutôt que d'entraîner un modèle unique conventionnel, qui donne souvent de mauvais résultats avec des données non identifiées, nous proposons un ensemble de règles centrées sur l'utilisateur qui produisent des modèles personnalisés adaptés aux objectifs de chaque utilisateur. Pour atténuer la surcharge de communication prohibitive associée à l'apprentissage d'un modèle personnalisé distinct pour chaque utilisateur, les utilisateurs sont répartis en groupes sur la base de la similarité de leurs objectifs. Cela permet l'apprentissage collectif de modèles personnalisés spécifiques à la cohorte. En conséquence, le nombre total de modèles personnalisés formés est réduit. Cette réduction diminue la consommation de ressources sans fil nécessaires à la transmission des mises à jour de modèles sur des canaux sans fil à bande passante limitée. Dans la deuxième partie, nous nous concentrons sur l'intégration des dispositifs à distance de l'IdO dans la périphérie intelligente en exploitant les véhicules aériens sans pilote en tant qu'orchestrateur d'apprentissage fédéré. Alors que des études antérieures ont largement exploré le potentiel des drones en tant que stations de base volantes ou relais dans les réseaux sans fil, leur utilisation pour faciliter l'apprentissage de modèles est encore un domaine de recherche relativement nouveau. Dans ce contexte, nous tirons parti de la mobilité des drones pour contourner les conditions de canal défavorables dans les zones rurales et établir des terrains d'apprentissage pour les dispositifs IoT distants. Cependant, les déploiements de drones posent des défis en termes de planification et de conception de trajectoires. À cette fin, une optimisation conjointe de la trajectoire du drone, de l'ordonnancement du dispositif et de la performance d'apprentissage est formulée et résolue à l'aide de techniques d'optimisation convexe et de la théorie des graphes. Dans la troisième partie de cette thèse, nous jetons un regard critique sur la surcharge de communication imposée par l'apprentissage fédéré sur les réseaux sans fil. Bien que les techniques de compression telles que la quantification et la sparsification des mises à jour de modèles soient largement utilisées, elles permettent souvent d'obtenir une efficacité de communication au prix d'une réduction de la performance du modèle. Pour surmonter cette limitation, nous utilisons des réseaux aléatoires sur-paramétrés pour approximer les réseaux cibles par l'élagage des paramètres plutôt que par l'optimisation directe. Il a été démontré que cette approche ne nécessite pas la transmission de plus d'un seul bit d'information par paramètre du modèle. Nous montrons que les méthodes SoTA ne parviennent pas à tirer parti de tous les avantages possibles en termes d'efficacité de la communication en utilisant cette approche. Nous proposons une fonction de perte régularisée qui prend en compte l'entropie des mises à jour transmises, ce qui se traduit par des améliorations notables de l'efficacité de la communication et de la mémoire lors de l'apprentissage fédéré sur des dispositifs périphériques, sans sacrifier la précisionIn the realm of future 6G wireless networks, integrating the intelligent edge through the advent of AI signifies a momentous leap forward, promising revolutionary advancements in wireless communication. This integration fosters a harmonious synergy, capitalizing on the collective potential of these transformative technologies. Central to this integration is the role of federated learning, a decentralized learning paradigm that upholds data privacy while harnessing the collective intelligence of interconnected devices. By embracing federated learning, 6G networks can unlock a myriad of benefits for both wireless networks and edge devices. On one hand, wireless networks gain the ability to exploit data-driven solutions, surpassing the limitations of traditional model-driven approaches. Particularly, leveraging real-time data insights will empower 6G networks to adapt, optimize performance, and enhance network efficiency dynamically. On the other hand, edge devices benefit from personalized experiences and tailored solutions, catered to their specific requirements. Specifically, edge devices will experience improved performance and reduced latency through localized decision-making, real-time processing, and reduced reliance on centralized infrastructure. In the first part of the thesis, we tackle the predicament of statistical heterogeneity in federated learning stemming from divergent data distributions among devices datasets. Rather than training a conventional one-model-fits-all, which often performs poorly with non-IID data, we propose user-centric set of rules that produce personalized models tailored to each user objectives. To mitigate the prohibitive communication overhead associated with training distinct personalized model for each user, users are partitioned into clusters based on their objectives similarity. This enables collective training of cohort-specific personalized models. As a result, the total number of personalized models trained is reduced. This reduction lessens the consumption of wireless resources required to transmit model updates across bandwidth-limited wireless channels. In the second part, our focus shifts towards integrating IoT remote devices into the intelligent edge by leveraging unmanned aerial vehicles as a federated learning orchestrator. While previous studies have extensively explored the potential of UAVs as flying base stations or relays in wireless networks, their utilization in facilitating model training is still a relatively new area of research. In this context, we leverage the UAV mobility to bypass the unfavorable channel conditions in rural areas and establish learning grounds to remote IoT devices. However, UAV deployments poses challenges in terms of scheduling and trajectory design. To this end, a joint optimization of UAV trajectory, device scheduling, and the learning performance is formulated and solved using convex optimization techniques and graph theory. In the third and final part of this thesis, we take a critical look at thecommunication overhead imposed by federated learning on wireless networks. While compression techniques such as quantization and sparsification of model updates are widely used, they often achieve communication efficiency at the cost of reduced model performance. We employ over-parameterized random networks to approximate target networks through parameter pruning rather than direct optimization to overcome this limitation. This approach has been demonstrated to require transmitting no more than a single bit of information per model parameter. We show that SoTA methods fail to capitalize on the full attainable advantages in terms of communication efficiency using this approach. Accordingly, we propose a regularized loss function which considers the entropy of transmitted updates, resulting in notable improvements to communication and memory efficiency during federated training on edge devices without sacrificing accuracy
32
Espinoza, Castellon Fabiola. "Contributions to effective and secure federated learning with client data heterogeneity". Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASG007.
Texto completo da fonteResumo:
Cette thèse se penche sur deux défis de l'apprentissage fédéré: l'hétérogénéité des données et la sécurité des modèles. Dans la première partie, nous nous attaquons à l'hétérogénéité des données, une problématique inhérente aux applications d'apprentissage fédéré dans un cadre réaliste. Les clients peuvent avoir des distributions de données différentes à cause de leurs opinions, localisations ou habitudes. Nous nous concentrons sur deux types distincts d'hétérogénéité dans les tâches de classification. Premièrement, quand les participants ont des distributions de données différentes mais similaires, l'apprentissage collaboratif est une approche attrayante. Notre première méthode s'appuie sur une approche d'adaptation de domaine collaborative, pour apprendre un dictionnaire empirique. Ce dictionnaire exprime les données de chaque client sous la forme d'une combinaison linéaire d'atomes, qui sont des ensembles empiriques représentant les données d'entraînement. Les clients apprennent les atomes en collaboration, tandis que les poids de la combinaison linéaire sont appris individuellement pour assurer la confidentialité. Ce dictionnaire est ensuite utilisé pour déduire les classes d'un client avec une distribution non étiquetée, mais qui a activement participé au processus d'apprentissage. Notre deuxième méthode traite une forme différente d'hétérogénéité, où les clients expriment des concepts différents dans leurs distributions. Dans ce cas, l'apprentissage collaboratif n'est pas toujours optimal, mais nous supposons qu'il existe une similarité structurelle entre les clients, qui nous permet de les regrouper pour un apprentissage plus efficace. Nous nous intéressons particulièrement à la "scalabilité" de cette méthode, en supposant un nombre élevé de participants. Notre approche est conçue pour estimer la structure cachée entre les clients à chaque agrégation des mises à jour des clients, de manière incrémentale. Contrairement à d'autres approches, nous n'imposons pas que tous les clients soient disponibles simultanément pour estimer leurs clusters d'appartenance. Dans la partie suivante de cette thèse, nous examinons les défis de sécurité de l'apprentissage fédéré, spécifiquement sur la vulnérabilité aux attaques par porte dérobée pendant l'apprentissage. Un système fédéré étant partagé, il est difficile d'assurer que tous les clients sont honnêtes et envoient des mises à jour correctes. L'apprentissage fédéré est vulnérable aux utilisateurs malveillants qui corrompent leurs données. Nos défenses sont conçues pour les attaques par porte dérobée, activées par des déclencheurs. Elles reposent sur la reconstruction de ces déclencheurs, sans fournir au serveur des données ou informations supplémentaires provenant des clients, à l'exception des poids compromis. En supposant certaines hypothèses limitées, le serveur peut estimer le déclencheur de l'attaque à partir du modèle global compromis. Notre troisième méthode utilise le déclencheur estimé pour identifier les neurones d'un réseau encodant l'attaque. Nous proposons d'élaguer ce réseau pour entraver les effets de l'attaque. Cette approche défend efficacement un modèle corrompu, même en présence de données hétérogènes. Enfin, notre dernière méthode déplace la défense vers les utilisateurs, en leur fournissant le déclencheur reconstruit pour contrer les attaques pendant la phase d'inférence. Cette défense se révèle particulièrement efficace même dans les cas extrêmes d'hétérogénéité. En conclusion, cette thèse introduit des méthodes novatrices pour améliorer l'efficacité et la sécurité des systèmes d'apprentissage fédérés. Nous avons exploré divers scénarios d'hétérogénéité des données, en proposant des approches d'apprentissage collaboratif et des défenses. Nous perspectives de recherche envisagent d'améliorer notre reconstruction des déclencheurs et en prenant en compte d'autres défis, tels que la confidentialité, qui est une aspect important en apprentissage fédéréThis thesis addresses two significant challenges in federated learning: data heterogeneity and security. In the first part of our work, we tackle the data heterogeneity challenge. Clients can have different data distributions due to their personal opinions, locations, habits, etc. It is a common and almost inherent obstacle in real-world federated learning applications. We focus on two distinct types of heterogeneity in classification tasks. On the one hand, in the first scenario, participants exhibit diverse yet related data distributions, making collaborative learning an attractive approach. Our first proposed method leverages a domain adaptation approach and collaboratively learns an empirical dictionary. A dictionary expresses each client's data as a linear combination of various atoms, that are a set of empirical samples representing the training data. Clients learn the atoms collaboratively, whereas they learn the weights privately to enhance privacy. Subsequently, the dictionary is utilized to infer classes for the clients' unlabeled distribution that withal actively participated in the learning process. On the other hand, our second method addresses a different form of data heterogeneity, where clients express different concepts through their distributions. Collaborative learning may not be optimal in this context; however, we assume a structural similarity between clients, enabling us to cluster them into groups for more effective group-based learning. In this case, we direct our attention to the scalability of our method by supposing that the number of participants can be very large. We propose to incrementally, each time the server aggregates the clients' updates, estimate the hidden structure between clients. Contrary to alternative approaches, we do not require that all be available at the same time to estimate their belonging clusters. In the second part of this thesis, we delve into the security challenges of federated learning, specifically focusing on defenses against training time backdoor attacks. Since a federated framework is shared, it is not always possible to ensure that all clients are honest and that they all send correctly trained updates.Federated learning is vulnerable to the presence of malicious users who corrupt their training data. Our defenses are elaborated for trigger-based backdoor attacks, and rooted in trigger reconstruction. We do not provide the server additional data or client information, other than the compromised weights. After some limited assumptions are made, the server extracts information about the attack trigger from the compromised model global model. Our third method uses a reconstructed trigger to identify the neurons of a neural network that encode the attack. We propose to prune the network on the server side to hinder the effects of the attack. Our final method shifts the defense mechanism to the end-users, providing them with the reconstructed trigger to counteract attacks during the inference phase. Notably, both defense methods consider data heterogeneity, with the latter proving to be more efficient in extreme data heterogeneity cases. In conclusion, this thesis introduces novel methods to enhance the efficiency and security of federated learning systems. We have explored diverse data heterogeneity scenarios, proposing collaborative learning approaches and robust security defenses based on trigger reconstruction. As part of our future work, we outline perspectives for further research, improving our proposed trigger reconstruction and taking into account other challenges, such as privacy which is very important in the field of federated learning
33
Hathurusinghe, Rajitha. "Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning". Thesis, Université d'Ottawa / University of Ottawa, 2020. http://hdl.handle.net/10393/41011.
Texto completo da fonteResumo:
This thesis explores the training of a deep neural network based named entity recognizer in
an end-to-end privacy preserved setting where dataset creation and model training happen
in an environment with minimal manual interventions. With the improvement of accuracy
in Deep Learning Models for practical tasks, a rising concern is satisfying the demand for
training data for these models amidst the concerns on the data privacy. Several scenarios of
data protection are suggested in the recent past due to public concerns hence the legal guidelines
to enforce them. A promising new development is the decentralized model training
on isolated datasets, which eliminates the compromises of privacy upon providing data to a
centralized entity. However, in this federated setting curating the data source is still a privacy
risk mostly in unstructured data sources such as text.
We explore the feasibility of automatic dataset annotation for a Named Entity Recognition
(NER) task and training a deep learning model with it in two federated learning settings.
We explore the feasibility of utilizing a dataset created in this manner for fine-tuning a stateof-
the-art deep learning language model for the downstream task of named entity recognition.
We also explore this novel setting of deep learning NLP model and federated learning
for its deviation from the classical centralized setting.
We created an automatically annotated dataset containing around 80,000 sentences, a
manual human annotated test set and tools to extend the dataset with more manual annotations.
We observed the noise from automated annotation can be overcome to a level by
increasing the dataset size. We also contributed to the federated learning framework with
state-of-the-art NLP model developments. Overall, our NER model achieved around 0.80
F1-score for recognition of entities in sentences.
34
Díaz, González Fernando. "Federated Learning for Time Series Forecasting Using LSTM Networks: Exploiting Similarities Through Clustering". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254665.
Texto completo da fonteResumo:
Federated learning poses a statistical challenge when training on highly heterogeneous sequence data. For example, time-series telecom data collected over long intervals regularly shows mixed fluctuations and patterns. These distinct distributions are an inconvenience when a node not only plans to contribute to the creation of the global model but also plans to apply it on its local dataset. In this scenario, adopting a one-fits-all approach might be inadequate, even when using state-of-the-art machine learning techniques for time series forecasting, such as Long Short-Term Memory (LSTM) networks, which have proven to be able to capture many idiosyncrasies and generalise to new patterns. In this work, we show that by clustering the clients using these patterns and selectively aggregating their updates in different global models can improve local performance with minimal overhead, as we demonstrate through experiments using realworld time series datasets and a basic LSTM model.Federated Learning utgör en statistisk utmaning vid träning med starkt heterogen sekvensdata. Till exempel så uppvisar tidsseriedata inom telekomdomänen blandade variationer och mönster över längre tidsintervall. Dessa distinkta fördelningar utgör en utmaning när en nod inte bara ska bidra till skapandet av en global modell utan även ämnar applicera denna modell på sin lokala datamängd. Att i detta scenario införa en global modell som ska passa alla kan visa sig vara otillräckligt, även om vi använder oss av de mest framgångsrika modellerna inom maskininlärning för tidsserieprognoser, Long Short-Term Memory (LSTM) nätverk, vilka visat sig kunna fånga komplexa mönster och generalisera väl till nya mönster. I detta arbete visar vi att genom att klustra klienterna med hjälp av dessa mönster och selektivt aggregera deras uppdateringar i olika globala modeller kan vi uppnå förbättringar av den lokal prestandan med minimala kostnader, vilket vi demonstrerar genom experiment med riktigt tidsseriedata och en grundläggande LSTM-modell.
35
Correia, Brum Rafaela. "Multi-FedLS : A Scheduler of Federated Learning Applications in a Multi-Cloud Environment". Electronic Thesis or Diss., Sorbonne université, 2023. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2023SORUS539.pdf.
Texto completo da fonteResumo:
L'apprentissage fédéré (AF) est un nouveau domaine de l'apprentissage machine distribué où l'apprentissage garantit la confidentialité des données. Chaque client a accès uniquement à son propre ensemble de données local et privé. Cette approche est attrayante dans divers domaines du savoir car elle permet à différentes institutions de collaborer sans partager leurs données confidentielles. Comme la quantité de données requises pour la formation a considérablement augmenté ces dernières années, la plupart des institutions ne peuvent pas se permettre des centres de données physiques pour stocker et manipuler l'ensemble de leurs données. Une option viable consiste à utiliser des services de stockage en nuage proposés par des fournisseurs offrant différentes garanties de confidentialité et de disponibilité des données. L'utilisateur est responsable du choix des régions où ses données sont stockées et du contrôle de leur accès.De plus, les fournisseurs de services en nuage offrent divers services pour exécuter une application. Ils permettent aux utilisateurs de créer des machines virtuelles (MV) avec différentes configurations, où les utilisateurs ont un contrôle total sur celles-ci. Ce type de service est appelé Infrastructure en tant que Service (IaaS). Ainsi, un environnement multi-cloud est propice à la collaboration de différentes institutions dans la création d'un modèle d'apprentissage machine grâce à l'apprentissage fédéré.Dans cette thèse, nous proposons Multi-FedLS, un framework robuste conçu pour exécuter des applications AF dans un environnement multi-cloud. Le framework prend en compte l'emplacement actuel des ensembles de données de chaque client, le délai de communication et le coût d'utilisation dans les nuages, en se concentrant sur la réduction des coûts et du temps d'exécution. De plus, Multi-FedLS utilise des instances moins chères chaque fois que possible pour réduire les coûts, même si elles peuvent être révoquées à tout moment par le fournisseur de services en nuage. Ainsi, pour assurer l'exécution réussie des applications AF, le cadre utilise des techniques de tolérance aux pannes telles que les points de contrôle et la migration des tâches pour reprendre la formation sur une autre MV après une révocation. Multi-FedLS comprend quatre modules: Pre-Scheduling, Initial Maping, Fault Tolerance e Dynamic Scheduler. Les résultats obtenus démontrent la faisabilité de l'exécution d'applications dans des environnements multi-cloud en utilisant des MV peu coûteuses, en utilisant une formulation mathématique, des techniques de tolérance aux pannes et des heuristiques simples pour la sélection de nouvelles MV. Le framework a obtenu une réduction des coûts de 56,92% par rapport au temps d'exécution de l'application en utilisant des MV plus coûteuses, avec seulement une augmentation de 5,44% du temps d'exécution sur les fournisseurs de services en nuage commerciauxFederated Learning (FL) is a new area of distributed Machine Learning (ML) where learning ensures data privacy. Each client has access only to its own local and private dataset. This approach is attractive in various domains of knowledge because it allows different institutions to collaborate without sharing their confidential data. As the amount of data required for training has grown significantly in recent years, most institutions cannot afford physical data centers to store and manipulate all their data. A viable option is to utilize cloud storage services offered by providers with different data privacy and availability guarantees. The user is responsible for choosing the regions where their data is stored and controlling access to it.Additionally, cloud providers offer various services to execute an application. They provide users with the ability to create Virtual Machines (VMs) with different configurations, where users have full control over them. This type of service is known as Infrastructure-as-a-Service (IaaS). Thus, a multi-cloud environment is conducive to the collaboration of different institutions in creating a Machine Learning model through Federated Learning.In this thesis, we propose extit{Multi-FedLS}, a robust framework designed to execute FL applications in a multi-cloud environment. The framework considers the current location of each client's datasets, communication delay, and cost of utilization in the clouds, focusing on cost and runtime reduction. Moreover, Multi-FedLS utilizes cheaper instances whenever possible to reduce costs, even though they may be revoked at any time by the cloud provider. Thus, to ensure the successful execution of FL applications, the framework employs fault-tolerance techniques such as checkpoints and work migration to resume training on another VM after a revocation. Multi-FedLS comprises four modules: Pre-Scheduling, Initial Mapping, Fault Tolerance, and Dynamic Scheduler. The obtained results demonstrate the feasibility of executing applications in multi-cloud environments using low-cost VMs, employing mathematical formulation, fault-tolerance techniques, and simple heuristics for selecting new VMs. The framework achieved a cost reduction of 56.92% compared to application runtime using more expensive VMs, with only a 5.44% increase in runtime on commercial cloud providers
36
Nan, Yucen. "High-Credibility Edge Analytic System for Early Medical Intervention". Thesis, The University of Sydney, 2022. https://hdl.handle.net/2123/27309.
Texto completo da fonteResumo:
The tremendous upsurge in the size of datasets has started gaining momentum a decade ago in science, finance, and every slice of our everyday life. The same scenario of the data volume explosion also arose in medical healthcare, and the elaborate management and exhaustive exploration of these heterogeneous data play important roles in modern medical care services. Traditional healthcare systems have been unable to cope with this complicated situation. After the popularity of digitized medical records and the evolution of the worldwide network interconnection, cloud computing has been proposed and successfully applied in healthcare with its advantages in competitive advantages, information sharing, and dynamic resources. However, along with the growing aspiration of patients, it is inevitable to gradually reform the structure of the healthcare system from the hospital-oriented centralized healthcare system to the patient-oriented distributed mobile healthcare systems (also termed as mHealth). Moreover, IoT (Internet of Things) provides an efficient and structured way to implement distributed patient-oriented mHealth systems, which inevitably leads to the exponential generation of medical data. To better adapt to the requirements (like time and energy consumption) of mHealth, edge computing has emerged as an effective implementation to complement and improve mobile healthcare systems supported by cloud computing. It is a big step to make healthcare systems more sensitive and flexible. Establishing the edge-based smart healthcare system is one of the best methods to alleviate the gigantic press on public medical care. This thesis aims to present the high-credibility edge analytic system for early medical intervention, covering every stage of the entire medical IoT ecosystem, which can be applied to non-specific or general disease treatments. This thesis summarizes the open issues for each stage within the system and further proposes corresponding solutions: from multi-view learning to improve learning performance to the implementation of interpretable results for medical prediction and analysis in conjunction with the outbreak of the COVID-19. And finally, under the consideration of the entire system architecture, security is guaranteed vertically interpretable analysis of edge distributed computing. These works cover almost all stages of the entire medical IoT ecosystem. We have given a variety of practical application scenarios and obtained the corresponding expected results through detailed and feasible experiments.
37
Horchidan, Sonia-Florina. "Real-time forecasting of dietary habits and user health using Federated Learning with privacy guarantees". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281366.
Texto completo da fonteResumo:
Modern health self-monitoring devices and applications, such as Fitbit and MyFitnessPal, empower users to take concrete actions and set fitness and lifestyle goals based on their recorded trends and statistics. Predicting such trends is beneficial in the road of achieving long-time targets, as the individuals can adjust their diets and habits at any point to guarantee success. The design and implementation of such a system, which also respects user privacy, is the main objective of our work.This application is modelled as a time-series forecasting problem. Given the historical data of users, we aim to predict their eating and lifestyle habits in real-time. We apply the federated learning paradigm to our use-case be- cause of the highly-distributed nature of our data and the privacy concerns of such sensitive recorded information. However, federated learning from het- erogeneous sequences of data can be challenging, as even state-of-the-art ma- chine learning techniques for time-series forecasting can encounter difficulties when learning from very irregular data sequences. Specifically, in the pro- posed healthcare scenario, the machine learning algorithms might fail to cater to users with unique dietary patterns.In this work, we implement a two-step streaming clustering mechanism and group clients that exhibit similar eating and fitness behaviours. The con- ducted experiments prove that learning federatively in this context can achieve very high prediction accuracy, as our predictions are no more than 0.025% far from the ground truth value with respect to the range of each feature. Training separate models for each group of users is shown to be beneficial, especially in terms of the training time, but it is highly dependent on the parameters used for the models and the training process. Our experiments conclude that the configuration used for the general federated model cannot be applied to the clusters of data. However, a decrease in prediction error of more than 45% can be achieved, given the parameters are optimized for each case.Lastly, this work tackles the problem of data privacy by applying state-of- the-art differential privacy techniques. Our empirical study shows that noising the gradients sent to the server is unsuitable for small datasets and cancels out the benefits obtained by prior users’ clustering. On the other hand, noising the training data achieves remarkable results, obtaining a differential privacy level corresponding to an epsilon value of 0.1 with an increase in the observed mean absolute error by a factor of only 0.21.Moderna apparater och applikationer för självövervakning av hälsa, som Fitbit och MyFitnessPal, ger användarna möjlighet att vidta konkreta åtgärder och sätta fitness- och livsstilsmål baserat på deras dokumenterade trender och statistik. Att förutsäga sådana trender är fördelaktigt för att uppnå långtidsmål, eftersom individerna kan anpassa sina dieter och vanor när som helst för att garantera framgång.Utformningen och implementeringen av ett sådant system, som dessutom respekterar användarnas integritet, är huvudmålet för vårt arbete. Denna appli- kation är modellerad som ett tidsserieprognosproblem. Med avseende på an- vändarnas historiska data är målet att förutsäga deras matvanor och livsstilsva- nor i realtid. Vi tillämpar det federerade inlärningsparadigmet på vårt använd- ningsfall på grund av den mycket distribuerade karaktären av vår data och in- tegritetsproblemen för sådan känslig bokförd information. Federerade lärande från heterogena datasekvenser kan emellertid vara utmanande, eftersom även de modernaste maskininlärningstekniker för tidsserieprognoser kan stöta på svårigheter när de lär sig från mycket oregelbundna datasekvenser. Specifikt i det föreslagna sjukvårdsscenariot kan maskininlärningsalgoritmerna misslyc- kas med att förse användare med unika dietmönster.I detta arbete implementerar vi en tvåstegsströmmande klustermekanism och grupperar användare som uppvisar liknande ät- och fitnessbeteenden. De genomförda experimenten visar att federerade lärande i detta sammanhang kan uppnå mycket hög nogrannhet i förutsägelse, eftersom våra förutsägelser in- te är mer än 0,025% ifrån det sanna värdet med avseende på intervallet för varje funktion. Träning av separata modeller för varje grupp användare visar sig vara fördelaktigt, särskilt gällande träningstiden, men det är mycket be- roende av parametrarna som används för modellerna och träningsprocessen. Våra experiment drar slutsatsen att konfigurationen som används för den all- männa federerade modellen inte kan tillämpas på dataklusterna. Dock kan en minskning av förutsägelsefel på mer än 45% uppnås, givet att parametrarna är optimerade för varje fall.Slutligen hanteras problemet med datasekretess genom att tillämpa bästa tillgängliga differentiell integritetsteknik. Vår empiriska studie visar att adde- ra brus till gradienter som skickas till servern är olämpliga för liten data och avbryter fördelarna med tidigare användares kluster. Däremot, genom att ad- dera brus till träningsdata uppnås anmärkningsvärda resultat. En differentierad integritetsnivå motsvarande ett epsilonvärde på 0,1 med en ökning av det ob- serverade genomsnittliga absoluta felet med en faktor på endast 0,21 erhölls.
38
Rinaldi, Riccardo. "Deployment e Gestione di Applicazioni di Federated Learning in Edge Cloud Computing basate sul Framework Fog05". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Encontre o texto completo da fonteResumo:
Il Federated Learning è la nuova branca del Machine Learning nata per sopperire al bisogno di nuovi sistemi architetturali che siano in grado di gestire i Big Data e allo stesso tempo garantire la privacy di eventuali dati sensibili. Per poter operare a queste due condizioni si è pensato di raccogliere i dati in un database centralizzato in modo che questi non lascino mai i margini della rete. Ecco perché è subentrato il mondo dell’edge computing in cui dispositivi intelligenti, posti tra il cloud e le Things, hanno il compito di pre-processare i dati raccolti per poi aggregarli su un unico server. Federated Learning e Edge/Cloud Computing sono due facce della stessa medaglia. I due mondi sono infatti profondamente interconnessi poiché fare Federated Learning vuol dire operare in un ambiente di tipo edge e cloud.
39
Almeida, Filho álvaro Cavalcanti de. "Modelo de mensuração do desempenho dos institutos federais: uma análise a partir de microdados". Universidade Federal da Paraíba, 2014. http://tede.biblioteca.ufpb.br:8080/handle/tede/5913.
Texto completo da fonteResumo:
Made available in DSpace on 2015-05-14T12:20:08Z (GMT). No. of bitstreams: 1
arquivototal.pdf: 2808387 bytes, checksum: 335548ec8225a562a073aa2415022046 (MD5)
Previous issue date: 2014-03-28Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES
This work presents a hermeneutic view of organizational learning based on the interpretation of public microdata provided by INEP and IBGE. We show an overview of the progress and challenges encountered with the expansion of basic education in the Federal Institutions (FI's) of the Brazilian Northeast, stimulating the creation of specific results in the Federal Network of Vocational Education, to assess the quality of public education in the PNE interval between 2001 and 2010. The purpose of this research is given by the reflection of Senge et al. (2005) on the significance of learning for an organization and the need to develop a clear and honest understanding of the reality. We apply concepts that relate to organizational knowledge creation with organizational learning for school management, measuring educational outcomes of 52 federal schools to answer questions related to overcoming regional disparities and assessing the quality of public education. Besides variables related to intra-school factors (school results, school infrastructure, human resources and student flow), we consider the exogenous factors (social context of students). Finally, we intend to contribute to the advancement of the discussion on equality and efficiency in the provision of quality public education, as required by Article 206 of the Constitution, from the identification of successful schools and the results that indicate the importance of the family background of students. The following aspects reverberate positively in the performance of students on the results of Enem in their different areas: the educational level of the parents, the level of household income and the frequency of the student in a private school in elementary phase (before entering FI).
Este trabalho traz uma visão hermenêutica da aprendizagem organizacional a partir da atribuição de significado a dados públicos existentes no acervo de microdados do INEP e IBGE. Apresenta uma visão dos avanços e desafios encontrados com a ampliação da oferta da educação básica nos IF s da Região Nordeste, favorecendo a criação de um lastro dos resultados específicos na Rede Federal de Educação Profissionalizante, para a avaliação da qualidade do ensino público no período de vigência do PNE 2001-2010. Tal avaliação da realidade do setor educacional, a que se propõe este trabalho, ressoa a reflexão de Senge et al. (2005) sobre o significado da aprendizagem para uma organização e a necessidade de desenvolver um entendimento claro e honesto da realidade. No curso do presente estudo, foram aplicados conceitos que fazem a ligação entre a criação de conhecimento organizacional e a aprendizagem organizacional, mormente, no âmbito da gestão escolar, haja vista a mensuração dos resultados educacionais de 52 escolas pertencentes a uma mesma rede de ensino, para responder a conflitos mais diretamente ligados à superação de assimetrias regionais e à avaliação da qualidade do ensino público compreendendo além de variáveis relativas aos fatores intraescolares (resultado escolar, infraestrutura escolar, recursos humanos e fluxo escolar), os fatores extraescolares (fatores do espaço social dos alunos). Tencionamos, pois, à guisa de conclusão, contribuir para o avanço do debate sobre a isonomia e eficiência na prestação do serviço público educacional, como prevê o artigo 206 da Constituição Federal, de garantia de padrão de qualidade para o ensino no país, sob uma tendência mimética das escolas bem-sucedidas e de resultados que sinalizam a necessidade de observância ao background familiar dos alunos dos IF s, uma vez que o grau de escolaridade dos pais do aluno, o nível da renda familiar e o aspecto de o aluno ter estudado o ensino fundamental em escola particular, antes do ingresso no IF, reverberam positivamente no desempenho dos discentes em proficiências nas áreas de conhecimento avaliadas pelo Enem.
40
Jiménez, Sánchez Amelia. "Learning representations for medical image diagnosis: impact of curriculum training and architectural design". Doctoral thesis, Universitat Pompeu Fabra, 2021. http://hdl.handle.net/10803/672839.
Texto completo da fonteResumo:
This thesis investigates two key aspects of learning deep-based image representations for medical diagnosis. The two are confronted with common challenges of medical image databases, namely, the limited number of samples, the presence of unreliable annotations and class-imbalance; as well as, domain shift and data privacy constraints for collaborative learning across institutions. The first part of this thesis concerns the architectural design of deep learning approaches. We explore the importance of localizing the region of interest in the image prior to the classification and the implicit capsule networks’ approach to model spatial information. We verify the importance of localization as a preliminary step to the classification, provide a sensitivity analysis of the size of the region of interest, and discuss image retrieval as a clinical use case. We also validate that capsules create equivariance, thus requiring to see fewer viewpoints of the object of interest. The second part of the thesis focuses on easing the optimization of the deep network parameters by gradually increasing the difficulty of the training samples. This gradual increase is based on the concept of curriculum learning and achieved with a data scheduler that controls the order and pace of the samples. We validate the beneficial effect of the curriculum data schedulers in two scenarios. First, we leveraged prior knowledge and uncertainty for the fine-grained classification of proximal femur fractures. In this case, we demonstrated the benefits of our proposed curriculum method under controlled scenarios: with limited amounts of data, under class-imbalance, and in the presence of label noise. Second, we verified the positive effect of the curriculum data scheduler for multi-site breast cancer classification in a federated learning setup.Esta tesis investiga dos aspectos fundamentales del aprendizaje de representaciones profundas de imágenes para el diagnóstico médico. Ambos se enfrentan a los retos comunes de las bases de datos de imágenes médicas, a saber, el número limitado de muestras, la presencia de anotaciones poco fiables y el desequilibrio de clases; así como, la adaptación al dominio (“domain adaptation”) y las restricciones de privacidad de datos para el aprendizaje colaborativo entre instituciones. La primera parte de esta tesis se centra en el diseño de arquitecturas para métodos de aprendizaje profundo (“deep learning”). Exploramos la importancia de localizar la región de interés en la imagen antes de la clasificación y el enfoque implícito de redes capsulares (“capsule networks”) para modelar la información espacial. Verificamos la importancia de la localización como paso previo a la clasificación, proporcionamos un análisis de sensibilidad del tamaño de la región de interés y discutimos la recuperación de imágenes como caso de uso clínico. También validamos que las cápsulas crean equidistancia, por lo que requieren ver menos puntos de vista del objeto de interés. La segunda parte de la tesis se enfoca en facilitar la optimización de los parámetros de la red aumentando gradualmente la dificultad de las muestras de entrenamiento. Este aumento gradual se basa en el concepto de aprendizaje curricular (“curriculum learning”) y se consigue con un programador de datos (“data scheduler”) que controla el orden y el ritmo de las muestras. Validamos el efecto beneficioso de los programadores de datos curriculares en dos escenarios. En primer lugar, aprovechamos el conocimiento previo y la incertidumbre para la clasificación granular de las fracturas de fémur proximal. En este caso, demostramos los beneficios de nuestro método basado en aprendizaje curricular bajo escenarios controlados: con cantidades limitadas de datos, desequilibrio de clases y en presencia de anotaciones imprecisas. En segundo lugar, verificamos el efecto positivo del planificador de datos para la clasificación del cáncer de mama en una configuración de aprendizaje federado (“federated learning”).
41
Cooper, Melissa. "Learning to lobby : the lessons of the NAACP's 1930s federal anti-lynching campaign". Thesis, University of East Anglia, 2017. https://ueaeprints.uea.ac.uk/67662/.
Texto completo da fonteResumo:
Why the NAACP pursued anti-lynching legislation with such vigour despite a decade of defeat in the Senate is the key research question this thesis considers. In doing so it analyses two aspects of the NAACP’s lobbying efforts during the 1930s: its attempts to push anti-lynching bills through Congress and its efforts to secure presidential endorsement for those bills. New insights on how the NAACP learned to lobby can be gleaned by considering the NAACP, Congress, and the President, as key influences on the anti-lynching campaign. This thesis analyses previously neglected primary source material to shed light on President Franklin D. Roosevelt’s influence on the anti-lynching campaign. Additionally, it interprets the anti-lynching campaign through a theoretical lens. It considers theories of lobbying in Congress, presidential power, and congressional obstruction to contextualise the institutions, politics, and politicians at play in the anti-lynching campaign. Despite no anti-lynching legislation ever being passed, both Congress and the executive branch had a profound effect upon the NAACP’s political education. In response to Congressional conservatism towards the anti-lynching campaign, and in order to push anti-lynching legislation through the legislative branch, the NAACP learned to overcome legislative obstruction and conform to norms and procedures dictated by Congress. By working with FDR—who, contrary to popular belief, had a liberal reformist attitude towards anti-lynching—the NAACP learned how to work with the executive branch and how to write stronger legislation. FDR helped NAACP activists to rhetorically frame anti-lynching in terms of the function of government and proposed strategies to give the federal government the power to prosecute lynchings. NAACP activists gained confidence in their tactics and optimism about achieving their objective from their political education. In contrast to the undertone of failure running through existing literature, the events of the anti-lynching movement instead highlight a theme of opportunity and hope for the NAACP.
42
Johnson, Gerald Deawne. "Development of an Audit Classification Index (ACI) for Federal e-learning Systems Security Vulnerabilities". NSUWorks, 2012. http://nsuworks.nova.edu/gscis_etd/187.
Texto completo da fonteResumo:
As U.S federal government agencies have increased the use of the Internet to utilize technologies such as e-learning, U.S. federal government information systems have become more exposed to security vulnerabilities that may contribute to system attacks and system exploitation. U.S. federal government agencies are required to come up with their own security solutions for ensuring their information systems are secured, however, security experts are having difficulties identifying what is needed to classify their information systems as secured.
The aim of this developmental study is to develop an audit classification index (ACI) to assist in identifying vulnerabilities and classifying electronic learning (e-learning) systems at U.S. federal government agencies. The study identified the requirements for performing an audit of e-learning systems in U.S. federal government agencies. After the requirements were identified, the study used the ACI to audit the federal e-learning systems using a black-box approach and classified the e-learning systems based on the results of the audit. Additionally, a comparative group of electronic government (e-government) systems were also audited and classified using the ACI to compare the results against the e-learning systems.
This study sought to contribute to the body of knowledge regarding the information security of U.S. federal e-learning systems by developing an ACI that can be used to identify vulnerabilities and classify U.S. federal e-learning systems as secured, good, marginal, unsatisfactory, or unsecured. By identifying the vulnerabilities of a particular information system, security experts should have a better understanding of what is needed to secure and determine the security level of U.S. federal information systems.
43
Morton, Shirley T. "Socialization-related learning, job satisfaction, and commitment for new employees in a federal agency". Diss., Virginia Tech, 1993. http://hdl.handle.net/10919/38548.
Texto completo da fonte
44
Alvelos, José Manuel Pinto. "Inovação, financiamento e aprendizado : o caso da Universidade Federal de Sergipe". Universidade Federal de Sergipe, 2008. https://ri.ufs.br/handle/riufs/4541.
Texto completo da fonteResumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorParting from Schumpeter s determinants of investment, an Evolutionary Theory is developed and with a base on the gene, identifying elements that encode routines and develop skills, establishing control, copying and imitation. Scientific technological knowledge, thus generated, can be created or replicated locally, creating what is called a "cluster of knowledge", leading to a dynamic Local Base of Innovation. A Federal Institution (FI) has two complementary roles: training human resources and accumulating techno-scientific knowledge to contribute to the implementation of a local socio-economy. These functions require a pattern of financing, which on the internal side, are derived by the application of "models of partition of OCC (Other Expenses and Capital)" by MEC / SESu determined by the Student-Equivalent Model, that is insufficient to take account the expansion plans of IFES. On the other hand, IFES seek external support to complement funding limitations via Projects, Programs, Parliamentary Amendments, among others, as was the case with UFS. To give consistency to our analysis, the case of the UFS was investigated, by historically analyzing results of approximately 10 years based on critical variables and parameters that make up the Student-Equivalent Model. We detected, despite the rapid growth of these variables, that elements of external and extra-budgetary partnerships were essential, illustrated by the examples of the NUPEG-SE and REUNI. The patterns of internal funding, allied by external partnerships, helped pave the way to consolidate UFS in its role as the Base of Local Innovation.
A partir dos determinantes Schumpeterianos do Investimento, desenvolvemos a Teoria Evolucionária e, com base no gene, apontamos os elementos que codificam a rotina e desenvolvem habilidades, estabelecendo o controle, a cópia e a imitação. O conhecimento científico-tecnológico, assim gerado, pode ser criado ou replicado localmente, originando o chamado cluster de conhecimento , dinamizando uma Base Local de Inovação. Uma Instituição Federal de Esnsino Superior (IFES) cumpre dois papéis complementares: formar recursos humanos e aportar conhecimentos tecnicocientíficos para a implementação de uma socioeconomia local. Essas funções exigem um padrão de financiamento que, pelo lado interno, resultam na aplicação de modelos de partição de OCC (Outros Custeios e Capital) pelo MEC/ SESu, sendo determinante o Aluno Equivalente ao se mostrar insuficiente para dar conta das pretensões de expansão das IFES . Por outro lado, as IFES buscam apoio externo e complementares para as suas carências de financiamento, mediante projetos, programas, emendas parlamentares, entre outras, como foi o caso da UFS. Para dar consistência à nossa análise aprofundamos o caso da UFS, recuperando historicamente, numa trajetória aproximada de 10 anos, as variáveis críticas e os parâmetros que compõem o Modelo Aluno-Equivalente. Detectamos, apesar do vigor de crescimento, que foram essenciais os elementos de parcerias externas e extra-orçamentárias, como o NUPEG-SE e o REUNI. Os padrões de financiamento interno, aliado às parcerias permitiram pavimentar o papel da UFS, para consolidação da Base Local de Inovação.
45
Subramanya, Tejas. "Autonomic Management and Orchestration Strategies in MEC-Enabled 5G Networks". Doctoral thesis, Università degli studi di Trento, 2021. http://hdl.handle.net/11572/320883.
Texto completo da fonteResumo:
5G and beyond mobile network technology promises to deliver unprecedented ultra-low latency and high data rates, paving the way for many novel applications and services. Network Function Virtualization (NFV) and Multi-access Edge Computing (MEC) are two technologies expected to play a vital role in achieving ambitious Quality of Service requirements of such applications. While NFV provides flexibility by enabling network functions to be dynamically deployed and inter-connected to realize Service Function Chains (SFC), MEC brings the computing capability to the mobile network's edges, thus reducing latency and alleviating the transport network load. However, adequate mechanisms are needed to meet the dynamically changing network service demands (i.e., in single and multiple domains) and optimally utilize the network resources while ensuring that the end-to-end latency requirement of services is always satisfied. In this dissertation work, we break the problem into three separate stages and present the solutions for each one of them.Firstly, we apply Artificial Intelligence (AI) techniques to drive NFV resource orchestration in MEC-enabled 5G architectures for single and multi-domain scenarios. We propose three deep learning approaches to perform horizontal and vertical Virtual Network Function (VNF) auto-scaling: (i) Multilayer Perceptron (MLP) classification and regression (single-domain), (ii) Centralized Artificial Neural Network (ANN), centralized Long-Short Term Memory (LSTM) and centralized Convolutional Neural Network-LSTM (CNN-LSTM) (single-domain), and (iii) Federated ANN, federated LSTM and federated CNN-LSTM (multi-domain). We evaluate the performance of each of these deep learning models trained over a commercial network operator dataset and investigate the pros and cons of different approaches for VNF auto-scaling. For the first approach, our results show that both MLP classifier and MLP regressor models have strong predicting capability for auto-scaling. However, MLP regressor outperforms MLP classifier in terms of accuracy. For the second approach (one-step prediction), CNN-LSTM performs the best for the QoS-prioritized objective and LSTM performs the best for the cost-prioritized objective. For the second approach (multi-step prediction), the encoder-decoder CNN-LSTM model outperforms the encoder-decoder LSTM model for both QoS and Cost prioritized objectives. For the third approach, both federated LSTM and federated CNN-LSTM models perform equally better than the federated ANN model. It was also noted that in general federated learning approaches performs poorly compared to centralized learning approaches. Secondly, we employ Integer Linear Programming (ILP) techniques to formulate and solve a joint user association and SFC placement problem, where each SFC represents a service requested by a user with end-to-end latency and data rate requirements. We also develop a comprehensive end-to-end latency model considering radio delay, backhaul network delay and SFC processing delay for 5G mobile networks. We evaluated the proposed model using simulations based on real-operator network topology and real-world latency values. Our results show that the average end-to-end latency reduces significantly when SFCs are placed at the ME hosts according to their latency and data rate demands. Furthermore, we propose an heuristic algorithm to address the issue of scalability in ILP, that can solve the above association/mapping problem in seconds rather than hours.Finally, we introduce lightMEC - a lightweight MEC platform for deploying mobile edge computing functionalities which allows hosting of low-latency and bandwidth-intensive applications at the network edge. Measurements conducted over a real-life test demonstrated that lightMEC could actually support practical MEC applications without requiring any change to existing mobile network nodes' functionality in the access and core network segments. The significant benefits of adopting the proposed architecture are analyzed based on a proof-of-concept demonstration of the content caching use case. Furthermore, we introduce the AI-driven Kubernetes orchestration prototype that we implemented by leveraging the lightMEC platform and assess the performance of the proposed deep learning models (from stage 1) in an experimental setup. The prototype evaluations confirm the simulation results achieved in stage 1 of the thesis.
46
Bhogi, Keerthana. "Two New Applications of Tensors to Machine Learning for Wireless Communications". Thesis, Virginia Tech, 2021. http://hdl.handle.net/10919/104970.
Texto completo da fonteResumo:
With the increasing number of wireless devices and the phenomenal amount of data that is being generated by them, there is a growing interest in the wireless communications community to complement the traditional model-driven design approaches with data-driven machine learning (ML)-based solutions. However, managing the large-scale multi-dimensional data to maintain the efficiency and scalability of the ML algorithms has obviously been a challenge. Tensors provide a useful framework to represent multi-dimensional data in an integrated manner by preserving relationships in data across different dimensions. This thesis studies two new applications of tensors to ML for wireless communications where the tensor structure of the concerned data is exploited in novel ways.
The first contribution of this thesis is a tensor learning-based low-complexity precoder codebook design technique for a full-dimension multiple-input multiple-output (FD-MIMO) system with a uniform planar antenna (UPA) array at the transmitter (Tx) whose channel distribution is available through a dataset. Represented as a tensor, the FD-MIMO channel is further decomposed using a tensor decomposition technique to obtain an optimal precoder which is a function of Kronecker-Product (KP) of two low-dimensional precoders, each corresponding to the horizontal and vertical dimensions of the FD-MIMO channel. From the design perspective, we have made contributions in deriving a criterion for optimal product precoder codebooks using the obtained low-dimensional precoders. We show that this product codebook design problem is an unsupervised clustering problem on a Cartesian Product Grassmann Manifold (CPM), where the optimal cluster centroids form the desired codebook. We further simplify this clustering problem to a $K$-means algorithm on the low-dimensional factor Grassmann manifolds (GMs) of the CPM which correspond to the horizontal and vertical dimensions of the UPA, thus significantly reducing the complexity of precoder codebook construction when compared to the existing codebook learning techniques.
The second contribution of this thesis is a tensor-based bandwidth-efficient gradient communication technique for federated learning (FL) with convolutional neural networks (CNNs). Concisely, FL is a decentralized ML approach that allows to jointly train an ML model at the server using the data generated by the distributed users coordinated by a server, by sharing only the local gradients with the server and not the raw data. Here, we focus on efficient compression and reconstruction of convolutional gradients at the users and the server, respectively. To reduce the gradient communication overhead, we compress the sparse gradients at the users to obtain their low-dimensional estimates using compressive sensing (CS)-based technique and transmit to the server for joint training of the CNN. We exploit a natural tensor structure offered by the convolutional gradients to demonstrate the correlation of a gradient element with its neighbors. We propose a novel prior for the convolutional gradients that captures the described spatial consistency along with its sparse nature in an appropriate way. We further propose a novel Bayesian reconstruction algorithm based on the Generalized Approximate Message Passing (GAMP) framework that exploits this prior information about the gradients. Through the numerical simulations, we demonstrate that the developed gradient reconstruction method improves the convergence of the CNN model.Master of Science
The increase in the number of wireless and mobile devices have led to the generation of massive amounts of multi-modal data at the users in various real-world applications including wireless communications. This has led to an increasing interest in machine learning (ML)-based data-driven techniques for communication system design. The native setting of ML is {em centralized} where all the data is available on a single device. However, the distributed nature of the users and their data has also motivated the development of distributed ML techniques. Since the success of ML techniques is grounded in their data-based nature, there is a need to maintain the efficiency and scalability of the algorithms to manage the large-scale data. Tensors are multi-dimensional arrays that provide an integrated way of representing multi-modal data. Tensor algebra and tensor decompositions have enabled the extension of several classical ML techniques to tensors-based ML techniques in various application domains such as computer vision, data-mining, image processing, and wireless communications. Tensors-based ML techniques have shown to improve the performance of the ML models because of their ability to leverage the underlying structural information in the data. In this thesis, we present two new applications of tensors to ML for wireless applications and show how the tensor structure of the concerned data can be exploited and incorporated in different ways. The first contribution is a tensor learning-based precoder codebook design technique for full-dimension multiple-input multiple-output (FD-MIMO) systems where we develop a scheme for designing low-complexity product precoder codebooks by identifying and leveraging a tensor representation of the FD-MIMO channel. The second contribution is a tensor-based gradient communication scheme for a decentralized ML technique known as federated learning (FL) with convolutional neural networks (CNNs), where we design a novel bandwidth-efficient gradient compression-reconstruction algorithm that leverages a tensor structure of the convolutional gradients. The numerical simulations in both applications demonstrate that exploiting the underlying tensor structure in the data provides significant gains in their respective performance criteria.
47
Silva, André Hellvig da. "JOGOS COMPUTACIONAIS NO ENSINO TÉCNICO PROFISSIONAL DO INSTITUTO FEDERAL FARROUPILHA: PANORAMA E POSSIBILIDADES". Universidade Federal de Santa Maria, 2015. http://repositorio.ufsm.br/handle/1/10668.
Texto completo da fonteResumo:
This paper assumes that the student may be motivated to seek knowledge through various mechanisms, and many include the challenge and the joy of accomplishment as a strategy, which is known as a reward paradigm. This research aims to detect the current level of use of computer games as a tool for learning in vocational technical education at the Federal Institute Farroupilha (IF Farroupilha) and in a second step, analyze the potential unexplored games most cited on this. After submitting an online questionnaire to a group of teachers of IF Farroupilha, the information was analyzed, highlighting the three computer games most commonly used by them. The second part of relapsed analysis of the cognitive potential of, relating to, as a result, the characteristics of each of the analyzed games. The findings show that most teachers want to take games as an important tool in the learning process. However, point out difficulties in finding games that meet the needs related to the educational level in which they operate, indicating as necessary features to games the existence of mechanisms of adaptation to the level of knowledge shown by the user, collaborative environment, and multidisciplinary approach to content.O presente trabalho parte do pressuposto que o discente pode ser motivado a buscar conhecimento por meio de diversos mecanismos, e muitos incluem o desafio e o prazer da conquista como estratégia, fato conhecido como paradigma da recompensa. Esta pesquisa tem o objetivo de detectar o atual nível de utilização de jogos computacionais como ferramenta de auxílio ao aprendizado no ensino técnico profissional no Instituto Federal Farroupilha (IF Farroupilha), bem como, em um segundo momento, analisar o potencial ainda não explorado dos jogos mais citados nesta. Após a submissão de um questionário online ao grupo de docentes do IF Farroupilha, as informações foram analisadas, destacando-se os três jogos computacionais mais utilizados pelos mesmos. A segunda parte da análise recaiu sobre o potencial cognitivo destes, relatando-se, na sequência, as características de cada um dos jogos analisados. As conclusões mostram que a maioria dos docentes deseja adotar jogos como ferramentas auxiliares no processo de aprendizagem. Porém, apontam dificuldades em encontrar jogos que satisfaçam as necessidades relativas ao nível educacional em que atuam, indicando como características necessárias aos jogos a existência de mecanismos de adaptação ao nível de conhecimento demonstrado pelo usuário, ambiente colaborativo, e abordagem multidisciplinar dos conteúdos.
48
Sugianto, Nehemia. "Responsible AI for Automated Analysis of Integrated Video Surveillance in Public Spaces". Thesis, Griffith University, 2021. http://hdl.handle.net/10072/409586.
Texto completo da fonteResumo:
Understanding customer experience in real-time can potentially support people’s safety and comfort while in public spaces. Existing techniques, such as surveys and interviews, can only analyse data at specific times. Therefore, organisations that manage public spaces, such as local government or business entities, cannot respond immediately when urgent actions are needed. Manual monitoring through surveillance cameras can enable organisation personnel to observe people. However, fatigue and human distraction during constant observation cannot ensure reliable and timely analysis. Artificial intelligence (AI) can automate people observation and analyse their movement and any related properties in real-time. Analysing people’s facial expressions can provide insight into how comfortable they are in a certain area, while analysing crowd density can inform us of the area’s safety level. By observing the long-term patterns of crowd density, movement, and spatial data, the organisation can also gain insight to develop better strategies for improving people’s safety and comfort.
There are three challenges to making an AI-enabled video surveillance system work well in public spaces. First is the readiness of AI models to be deployed in public space settings. Existing AI models are designed to work in generic/particular settings and will suffer performance degradation when deployed in a real-world setting. Therefore, the models require further development to tailor them for the specific environment of the targeted deployment setting. Second is the inclusion of AI continual learning capability to adapt the models to the environment. AI continual learning aims to learn from new data collected from cameras to adapt the models to constant visual changes introduced in the setting. Existing continuous learning approaches require long-term data retention and past data, which then raise data privacy issues. Third, most of the existing AI-enabled surveillance systems rely on centralised processing, meaning data are transmitted to a central/cloud machine for video analysis purposes. Such an approach involves data privacy and security risks. Serious data threats, such as data theft, eavesdropping or cyberattack, can potentially occur during data transmission.
This study aims to develop an AI-enabled intelligent video surveillance system based on deep learning techniques for public spaces established on responsible AI principles. This study formulates three responsible AI criteria, which become the guidelines to design, develop, and evaluate the system. Based on the criteria, a framework is constructed to scale up the system over time to be readily deployed in a specific real-world environment while respecting people’s privacy. The framework incorporates three AI learning approaches to iteratively refine the AI models within the ethical use of data. First is the AI knowledge transfer approach to adapt existing AI models from generic deployment to specific real-world deployment with limited surveillance datasets. Second is the AI continuous learning approach to continuously adapt AI models to visual changes introduced by the environment without long-period data retention and the need for past data. Third is the AI federated learning approach to limit sensitive and identifiable data transmission by performing computation locally on edge devices rather than transmitting to the central machine.
This thesis contributes to the study of responsible AI specifically in the video surveillance context from both technical and non-technical perspectives. It uses three use cases at an international airport as the application context to understand passenger experience in real-time to ensure people’s safety and comfort. A new video surveillance system is developed based on the framework to provide automated people observation in the application context. Based on real deployment using the airport’s selected cameras, the evaluation demonstrates that the system can provide real-time automated video analysis for three use cases while respecting people’s privacy. Based on comprehensive experiments, AI knowledge transfer can be an effective way to address limited surveillance datasets issue by transferring knowledge from similar datasets rather than training from scratch on surveillance datasets. It can be further improved by incrementally transferring knowledge from multi-datasets with smaller gaps rather than a one-stage process. Learning without Forgetting is a viable approach for AI continuous learning in the video surveillance context. It consistently outperforms fine-tuning and joint-training approaches with lower data retention and without the need for past data. AI federated learning can be a feasible solution to allow continuous learning in the video surveillance context without compromising model accuracy. It can obtain comparable accuracy with quicker training time compared to joint-training.Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
Dept Bus Strategy & Innovation
Griffith Business School
Full Text
49
Di, Donato Davide. "Sviluppo, Deployment e Validazione Sperimentale di Architetture Distribuite di Machine Learning su Piattaforma fog05". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19021/.
Texto completo da fonteResumo:
Ultimamente sta crescendo sempre di più l'interesse riguardo al fog computing e alle possibilità che offre, tra cui la capacità di poter fruire di una capacità computazionale considerevole anche nei nodi più vicini all’utente finale: questo permetterebbe di migliorare diversi parametri di qualità di un servizio come la latenza nella sua fornitura e il costo richiesto per le comunicazioni.
In questa tesi, sfruttando le considerazioni sopra, abbiamo creato e testato due architetture di machine learning distribuito e poi le abbiamo utilizzate per fornire un servizio di predizione (legato al condition monitoring) che migliorasse la soluzione cloud relativamente ai parametri citati prima. Poi, è stata utilizzata la piattaforma fog05, un tool che permette la gestione efficiente delle varie risorse presenti in una rete, per eseguire il deployment delle architetture sopra.
Gli obiettivi erano due: validare le architetture in termini di accuratezza e velocità di convergenza e confermare la capacità di fog05 di gestire deployment complessi come quelli necessari nel nostro caso.
Innanzitutto, sono state scelte le architetture: per una, ci siamo basati sul concetto di gossip learning, per l'altra, sul federated learning. Poi, queste architetture sono state implementate attraverso Keras e ne è stato testato il funzionamento: è emerso chiaramente come, in casi d'uso come quello in esame, gli approcci distribuiti riescano a fornire performance di poco inferiori a una soluzione centralizzata. Infine, è stato eseguito con successo il deployment delle architetture utilizzando fog05, incapsulando le funzionalità di quest'ultimo dentro un orchestratore creato ad-hoc al fine di gestire nella maniera più automatizzata e resiliente possibile la fornitura del servizio offerto dalle architetture sopra.
50
Gormbley, Edward Z. "The hope and lifetime learning credits: the political sociology of federal financial aid for undergraduate education". Thesis, Boston University, 2000. https://hdl.handle.net/2144/32868.
Texto completo da fonteResumo:
Thesis (B.A.)--Boston University. University Professors Program Senior theses.PLEASE NOTE: Boston University Libraries did not receive an Authorization To Manage form for this thesis. It is therefore not openly accessible, though it may be available by request. If you are the author or principal advisor of this work and would like to request open access for it, please contact us at open-help@bu.edu. Thank you.
2031-01-01