Thèses sur le sujet « Recommendation graph »
Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Recommendation graph.
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 40 meilleures thèses pour votre recherche sur le sujet « Recommendation graph ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
1
Huang, Zan. « GRAPH-BASED ANALYSIS FOR E-COMMERCE RECOMMENDATION ». Diss., Tucson, Arizona : University of Arizona, 2005. http://etd.library.arizona.edu/etd/GetFileServlet?file=file:///data1/pdf/etd/azu%5Fetd%5F1167%5F1%5Fm.pdf&type=application/pdf.
Texte intégral
2
Larsson, Carl-Johan. « Movie Recommendation System Using Large Scale Graph-Processing ». Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-200601.
Texte intégral
3
Söderkvist, Nils. « Recommendation system for job coaches ». Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-446792.
Texte intégralRésumé :
For any unemployed person in Sweden that is looking for a job, the most common place they can turn to is the Swedish Public Employment Service, also known as Arbetsförmedlingen, where they can register to get help with the job search process. Occasionally, in order to land an employment, the person might require extra guidance and education, Arbetsförmedlingen outsource this education to external companies called providers where each person gets assigned a coach that can assist them in achieving an employment quicker. Given the current labour market data, can the data be used to help optimize and speed up the job search process? To try and help optimize the process, the labour market data was inserted into a graph database, using the database, a recommendation system was built which uses different methods to perform each recommendation. The recommendations can be used by a provider to assist them in assigning coaches to newly registered participants as well as recommending activities. The performance of each recommendation method was evaluated using a statistic measure. While the user-created methods had acceptable performance, the overall best performing recommendation method was collaborative filtering. However, there are definitely some potential for the user-created method, and given some additional testing and tuning, the methods can surely outperform the collaborative filtering method. In addition, expanding the database by adding more data would positively affect the recommendations as well.
4
Ozturk, Gizem. « A Hybrid Veideo Recommendation System Based On A Graph Based Algorithm ». Master's thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/12612624/index.pdf.
Texte intégralRésumé :
This thesis proposes the design, development and evaluation of a hybrid video
recommendation system. The proposed hybrid video recommendation system is based
on a graph algorithm called Adsorption. Adsorption is a collaborative filtering algorithm
in which relations between users are used to make recommendations. Adsorption is used
to generate the base recommendation list. In order to overcome the problems that occur
in pure collaborative system, content based filtering is injected. Content based filtering
uses the idea of suggesting similar items that matches user preferences. In order to use
content based filtering, first, the base recommendation list is updated by removing weak
recommendations. Following this, item similarities of the remaining list are calculated
and new items are inserted to form the final recommendations. Thus, collaborative
recommendations are empowered considering item similarities. Therefore, the
developed hybrid system combines both collaborative and content based approaches to
produce more effective suggestions.
5
Landia, Nikolas. « Content-awareness and graph-based ranking for tag recommendation in folksonomies ». Thesis, University of Warwick, 2013. http://wrap.warwick.ac.uk/58069/.
Texte intégralRésumé :
Tag recommendation algorithms aid the social tagging process in many userdriven document indexing applications, such as social bookmarking and publication sharing websites. This thesis gives an overview of existing tag recommendation methods and proposes novel approaches that address the new document problem and the task of ranking tags. The focus is on graph-based methods such as Folk- Rank that apply weight spreading algorithms to a graph representation of the folksonomy. In order to suggest tags for previously untagged documents, extensions are presented that introduce content into the recommendation process as an additional information source. To address the problem of ranking tags, an in-depth analysis of graph models as well as ranking algorithms is conducted. Implicit assumptions made by the widely-used graph model of the folksonomy are highlighted and an improved model is proposed that captures the characteristics of the social tagging data more accurately. Additionally, issues in the tag rank computation of FolkRank are analysed and an adapted weight spreading approach for social tagging data is presented. Moreover, the applicability of conventional weight spreading methods to data from the social tagging domain is examined in detail. Finally, indications of implicit negative feedback in the data structure of folksonomies are analysed and novel approaches of identifying negative relationships are presented. By exploiting the three-dimensional characteristics of social tagging data the proposed metrics are based on stronger evidence and provide reliable measures of negative feedback. Including content into the tag recommendation process leads to a significant increase in recommendation accuracy on real-world datasets. The proposed adaptations to graph models and ranking algorithms result in more accurate and computationally less expensive recommenders. Moreover, new insights into the fundamental characteristics of social tagging data are revealed and a novel data interpretation that takes negative feedback into account is proposed.
6
Priya, Rashmi. « RETAIL DATA ANALYTICS USING GRAPH DATABASE ». UKnowledge, 2018. https://uknowledge.uky.edu/cs_etds/67.
Texte intégralRésumé :
Big data is an area focused on storing, processing and visualizing huge amount of data. Today data is growing faster than ever before. We need to find the right tools and applications and build an environment that can help us to obtain valuable insights from the data. Retail is one of the domains that collects huge amount of transaction data everyday. Retailers need to understand their customer’s purchasing pattern and behavior in order to take better business decisions.
Market basket analysis is a field in data mining, that is focused on discovering patterns in retail’s transaction data. Our goal is to find tools and applications that can be used by retailers to quickly understand their data and take better business decisions. Due to the amount and complexity of data, it is not possible to do such activities manually. We witness that trends change very quickly and retailers want to be quick in adapting the change and taking actions. This needs automation of processes and using algorithms that are efficient and fast. In our work, we mine transaction data by modeling the data as graphs. We use clustering algorithms to discover communities (clusters) in the data and then use the clusters for building a recommendation system that can recommend products to customers based on their buying behavior.
7
Olmucci, Poddubnyy Oleksandr. « Graph Neural Networks for Recommender Systems ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022. http://amslaurea.unibo.it/25033/.
Texte intégralRésumé :
In recent years, a new type of deep learning models, Graph Neural Networks (GNNs), have demonstrated to be a powerful learning paradigm when applied to problems that can be described via graph data, due to their natural ability to integrate representations across nodes that are connected via some topological structure. One of such domains is Recommendation Systems, the majority of whose data can be naturally represented via graphs. For example, typical item recommendation datasets can be represented via user-item bipartite graphs, social recommendation datasets by social networks, and so on. The successful application of GNNs to the field of recommendation, is demonstrated by the state of the art results achieved on various datasets, making GNNs extremely appealing in this domain, also from a commercial perspective. However, the introduction of graph layers and their associated sampling techniques significantly affects the nature of the calculations that need to be performed on GPUs, the main computational accelerator used nowadays: something that hasn't been investigated so far by any of the architectures in the recommendation literature. This thesis aims to fill this gap by conducting the first systematic empirical investigation of GNN-based architectures for recommender systems, focusing on their multi-GPU scalability and precision speed-up properties, when using different types of hardware.
8
Bereczki, Márk. « Graph Neural Networks for Article Recommendation based on Implicit User Feedback and Content ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-300092.
Texte intégralRésumé :
Recommender systems are widely used in websites and applications to help users find relevant content based on their interests. Graph neural networks achieved state- of-the- art results in the field of recommender systems, working on data represented in the form of a graph. However, most graph- based solutions hold challenges regarding computational complexity or the ability to generalize to new users. Therefore, we propose a novel graph- based recommender system, by modifying Simple Graph Convolution, an approach for efficient graph node classification, and add the capability of generalizing to new users. We build our proposed recommender system for recommending the articles of Peltarion Knowledge Center. By incorporating two data sources, implicit user feedback based on pageview data as well as the content of articles, we propose a hybrid recommender solution. Throughout our experiments, we compare our proposed solution with a matrix factorization approach as well as a popularity- based and a random baseline, analyse the hyperparameters of our model, and examine the capability of our solution to give recommendations to new users who were not part of the training data set. Our model results in slightly lower, but similar Mean Average Precision and Mean Reciprocal Rank scores to the matrix factorization approach, and outperforms the popularity- based and random baselines. The main advantages of our model are computational efficiency and its ability to give relevant recommendations to new users without the need for retraining the model, which are key features for real- world use cases.Rekommendationssystem används ofta på webbplatser och applikationer för att hjälpa användare att hitta relevant innehåll baserad på deras intressen. Med utvecklingen av grafneurala nätverk nådde toppmoderna resultat inom rekommendationssystem och representerade data i form av en graf. De flesta grafbaserade lösningar har dock svårt med beräkningskomplexitet eller att generalisera till nya användare. Därför föreslår vi ett nytt grafbaserat rekommendatorsystem genom att modifiera Simple Graph Convolution. De här tillvägagångssätt är en effektiv grafnodsklassificering och lägga till möjligheten att generalisera till nya användare. Vi bygger vårt föreslagna rekommendatorsystem för att rekommendera artiklarna från Peltarion Knowledge Center. Genom att integrera två datakällor, implicit användaråterkoppling baserad på sidvisningsdata samt innehållet i artiklar, föreslår vi en hybridrekommendatörslösning. Under våra experiment jämför vi vår föreslagna lösning med en matrisfaktoriseringsmetod samt en popularitetsbaserad och en slumpmässig baslinje, analyserar hyperparametrarna i vår modell och undersöker förmågan hos vår lösning att ge rekommendationer till nya användare som inte deltog av träningsdatamängden. Vår modell resulterar i något mindre men liknande Mean Average Precision och Mean Reciprocal Rank poäng till matrisfaktoriseringsmetoden och överträffar de popularitetsbaserade och slumpmässiga baslinjerna. De viktigaste fördelarna med vår modell är beräkningseffektivitet och dess förmåga att ge relevanta rekommendationer till nya användare utan behov av omskolning av modellen, vilket är nyckelfunktioner för verkliga användningsfall.
9
You, Di. « Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation ». Digital WPI, 2019. https://digitalcommons.wpi.edu/etd-theses/1321.
Texte intégralRésumé :
To combat fake news, researchers mostly focused on detecting fake news and journalists built and maintained fact-checking sites (e.g., Snopes.com and Politifact.com). However, fake news dissemination has been greatly promoted by social media sites, and these fact-checking sites have not been fully utilized. To overcome these problems and complement existing methods against fake news, in this thesis, we propose a deep-learning based fact-checking URL recommender system to mitigate impact of fake news in social media sites such as Twitter and Facebook. In particular, our proposed framework consists of a multi-relational attentive module and a heterogeneous graph attention network to learn complex/semantic relationship between user-URL pairs, user-user pairs, and URL-URL pairs. Extensive experiments on a real-world dataset show that our proposed framework outperforms seven state-of-the-art recommendation models, achieving at least 3~5.3% improvement.
10
Lisena, Pasquale. « Knowledge-based music recommendation : models, algorithms and exploratory search ». Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS614.
Texte intégralRésumé :
Représenter l'information décrivant la musique est une activité complexe, qui implique différentes sous-tâches. Ce manuscrit de thèse porte principalement sur la musique classique et étudie comment représenter et exploiter ses informations. L'objectif principal est l'étude de stratégies de représentation et de découverte des connaissances appliquées à la musique classique, dans des domaines tels que la production de base de connaissances, la prédiction de métadonnées et les systèmes de recommandation. Nous proposons une architecture pour la gestion des métadonnées de musique à l'aide des technologies du Web Sémantique. Nous introduisons une ontologie spécialisée et un ensemble de vocabulaires contrôlés pour les différents concepts spécifiques à la musique. Ensuite, nous présentons une approche de conversion des données, afin d’aller au-delà de la pratique bibliothécaire actuellement utilisée, en s’appuyant sur des règles de mapping et sur l’interconnexion avec des vocabulaires contrôlés. Enfin, nous montrons comment ces données peuvent être exploitées. En particulier, nous étudions des approches basées sur des plongements calculés sur des métadonnées structurées, des titres et de la musique symbolique pour classer et recommander de la musique. Plusieurs applications de démonstration ont été réalisées pour tester les approches et les ressources précédentesRepresenting the information about music is a complex activity that involves different sub-tasks. This thesis manuscript mostly focuses on classical music, researching how to represent and exploit its information. The main goal is the investigation of strategies of knowledge representation and discovery applied to classical music, involving subjects such as Knowledge-Base population, metadata prediction, and recommender systems. We propose a complete workflow for the management of music metadata using Semantic Web technologies. We introduce a specialised ontology and a set of controlled vocabularies for the different concepts specific to music. Then, we present an approach for converting data, in order to go beyond the librarian practice currently in use, relying on mapping rules and interlinking with controlled vocabularies. Finally, we show how these data can be exploited. In particular, we study approaches based on embeddings computed on structured metadata, titles, and symbolic music for ranking and recommending music. Several demo applications have been realised for testing the previous approaches and resources
11
Slaimi, Fatma. « Découverte et recommandation de services Web ». Thesis, Aix-Marseille, 2017. http://www.theses.fr/2017AIXM0069.
Texte intégralRésumé :
Le Web est devenu une plateforme universelle d’hébergement d'applications hétérogènes. Dans ce contexte, les services Web se sont imposés comme une technologie clé pour permettre l’interaction entre diverses applications. Les technologies standards proposées autour des services Web permettent la programmation, plutôt manuelle, de ces applications. Pour favoriser une programmation automatique à base de services web, un problème majeur se pose : celui de leur découverte. Plusieurs approches adressant ce problème ont été proposées dans la littérature. L’objectif de cette thèse est d’améliorer le processus de découverte de services en exploitant trois pistes de recherche. La première consiste à proposer une approche de découverte qui combine plusieurs techniques de matching. La deuxième se base sur une validation des services retournés par un processus de découverte automatique en se basant sur les compétences utilisateurs. Ces approches ne prennent pas en considération l’évolution de services dans le temps et les préférences des utilisateurs. Pour remédier à ces lacunes plusieurs approches incorporent des techniques de recommandation. La majorité d'entre eux sont basées sur les évaluations des propriétés de QdS. Pratiquement, ces évaluations sont rarement disponibles. D’autres systèmes exploitent les relations de confiance. Ces relations sont établies en se basant sur les évaluations de services. Or, invoquant le même service ne signifie pas obligatoirement avoir les mêmes préférences. D’où, nous proposons, l’exploitation des relations d’intérêts entre les utilisateurs pour recommander des services. L’approche s’appuie sur une modélisation orientée base de données graphesThe Web has become an universal platform for content hosting and distributed heterogeneous applications that can be accessed manually or automatically. In this context, Web services have established themselves as a key technology for deploying interactions across applications. The standard Web services technologies allow and facilitate the manual programming of these applications. To promote automatic programming based on Web services, a major problem arises : that of their discovery. Several approaches addressing this problem have been proposed in the literature. The aim of this thesis is to improve the Web services discovery process. We proposed three approaches. We proposed a Web services discovery approach that combines several matching techniques. The second consists on the validation of the services returned by an automatic process of discovery using users’ competencies. These approaches do not take into account the evolution of services over time and user preferences. To address these shortcomings, several approaches incorporate referral techniques to assist the discovery process. A large majority of these approaches are based on assessments of QoS properties. In practice, these assessments are rarely available. In other systems, trust relationships between users and services are used. These relationships are established based on invocations evaluations of similar services. However, invoking the same service do not necessarily mean having the same preferences. Hence, we propose, in our third approach, the use of the relations of interest between users to recommend services. The approach relies on modeling services’ ecosystem by database graphs
12
Betti, Andrea. « Studio e progettazione di tecniche per l'estrazione automatica di metadati relativi all'accessibilità delle risorse didattiche ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24969/.
Texte intégralRésumé :
Il progetto di tesi vede come oggetto lo sviluppo di un'applicazione web che permetta a studenti universitari di sottoporre le proprie generalità a un sistema di raccomandazione di corsi accademici e relative risorse didattiche associate, dando rilevanza anche alle eventuali disabilità possedute dallo studente.
Il modello di raccomandazione si basa su regole che estendono e inferiscono nuove relazioni semantiche tra i componenti dell'ontologia progettata per rappresentare i componenti del dominio, incorporando proprietà di ontologie già esistenti che modellano l'accessibilità delle risorse e l’organizzazione strutturale delle istituzioni educative.
L'applicazione permetterà inoltre ai docenti universitari di associare nuove risorse ai corsi di cui sono titolari, su cui verranno generati automaticamente metadati relativi alle proprietà del file e al suo contenuto. Questi metadati verranno utilizzati dal sistema di raccomandazione per suggerire risorse il cui grado di accessibilità secondo determinati aspetti, come la modalità di fruizione del contenuto o la sua trasformabilità, è compatibile con le eventuali disabilità possedute dallo studente.
Verranno inoltre analizzate varie tecniche di generazione automatica di metadati, il cui scopo è facilitare l'estrazione di informazioni da associare alle risorse.
13
Kucuktunc, Onur. « Result Diversification on Spatial, Multidimensional, Opinion, and Bibliographic Data ». The Ohio State University, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=osu1374148621.
Texte intégral
14
Nzekon, Nzeko'o Armel Jacques. « Système de recommandation avec dynamique temporelle basée sur les flots de liens ». Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS454.
Texte intégralRésumé :
La recommandation des produits appropriés aux clients est cruciale dans de nombreuses plateformes de e-commerce qui proposent un grand nombre de produits. Les systèmes de recommandation sont une solution favorite pour la réalisation de cette tâche. La majorité des recherches de ce domaine reposent sur des notes explicites que les utilisateurs attribuent aux produits, alors que la plupart du temps ces notes ne sont pas disponibles en quantité suffisante. Il est donc important que les systèmes de recommandation utilisent les données implicites que sont des flots de liens représentant les relations entre les utilisateurs et les produits, c'est-à-dire l'historique de navigation, des achats et de streaming. C'est ce type de données implicites que nous exploitons. Une approche populaire des systèmes de recommandation consiste, pour un entier N donné, à proposer les N produits les plus pertinents pour chaque utilisateur : on parle de recommandation top-N. Pour ce faire, bon nombre de travaux reposent sur des informations telles que les caractéristiques des produits, les goûts et préférences antérieurs des utilisateurs et les relations de confiance entre ces derniers. Cependant, ces systèmes n'utilisent qu'un ou deux types d'information simultanément, ce qui peut limiter leurs performances car l'intérêt qu'un utilisateur a pour un produit peut à la fois dépendre de plus de deux types d'information. Pour remédier à cette limite, nous faisons trois propositions dans le cadre des graphes de recommandation. La première est une extension du Session-based Temporal Graph (STG) introduit par Xiang et al., et qui est un graphe dynamique combinant les préférences à long et à court terme des utilisateurs, ce qui permet de mieux capturer la dynamique des préférences de ces derniers. STG ne tient pas compte des caractéristiques des produits et ne fait aucune différence de poids entre les arêtes les plus récentes et les arêtes les plus anciennes. Le nouveau graphe proposé, Time-weight content-based STG contourne les limites du STG en y intégrant un nouveau type de nœud pour les caractéristiques des produits et une pénalisation des arêtes les plus anciennes. La seconde contribution est un système de recommandation basé sur l'utilisation de Link Stream Graph (LSG). Ce graphe est inspiré d'une représentation des flots de liens et a la particularité de considérer le temps de manière continue contrairement aux autres graphes de la littérature, qui soit ignore la dimension temporelle comme le graphe biparti classique (BIP), soit considère le temps de manière discontinue avec un découpage du temps en tranches comme STGRecommending appropriate items to users is crucial in many e-commerce platforms that propose a large number of items to users. Recommender systems are one favorite solution for this task. Most research in this area is based on explicit ratings that users give to items, while most of the time, ratings are not available in sufficient quantities. In these situations, it is important that recommender systems use implicit data which are link stream connecting users to items while maintaining timestamps i.e. users browsing, purchases and streaming history. We exploit this type of implicit data in this thesis. One common approach consists in selecting the N most relevant items to each user, for a given N, which is called top-N recommendation. To do so, recommender systems rely on various kinds of information, like content-based features of items, past interest of users for items and trust between users. However, they often use only one or two such pieces of information simultaneously, which can limit their performance because user's interest for an item can depend on more than two types of side information. To address this limitation, we make three contributions in the field of graph-based recommender systems. The first one is an extension of the Session-based Temporal Graph (STG) introduced by Xiang et al., which is a dynamic graph combining long-term and short-term preferences in order to better capture user preferences over time. STG ignores content-based features of items, and make no difference between the weight of newer edges and older edges. The new proposed graph Time-weight Content-based STG addresses STG limitations by adding a new node type for content-based features of items, and a penalization of older edges. The second contribution is the Link Stream Graph (LSG) for temporal recommendations. This graph is inspired by a formal representation of link stream, and has the particularity to consider time in a continuous way unlike others state-of-the-art graphs, which ignore the temporal dimension like the classical bipartite graph (BIP), or consider time discontinuously like STG where time is divided into slices. The third contribution in this thesis is GraFC2T2, a general graph-based framework for top-N recommendation. This framework integrates basic recommender graphs, and enriches them with content-based features of items, users' preferences temporal dynamics, and trust relationships between them. Implementations of these three contributions on CiteUlike, Delicious, Last.fm, Ponpare, Epinions and Ciao datasets confirm their relevance
15
Poulain, Rémy. « Analyse et modélisation de la diversité des structures relationnelles à l'aide de graphes multipartis ». Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS453.
Texte intégralRésumé :
Il n’est plus à prouver que le numérique, Internet et le web ont entraîné une révolution notamment dans la manière de s’informer. Comme toute révolution, elle est suivie par une série d’enjeux : égalité de traitement des utilisateurs et des fournisseurs, consommations écologiquement durables, liberté d’expression et censure, etc. Il est nécessaire que la recherche apporte une vision claire de ces enjeux. Parmi ces enjeux, nous pouvons parler de deux phénomènes : le phénomène de chambre d’écho et le phénomène de bulle de filtre. Ces deux phénomènes sont liés au manque de diversité de l’information visible sur internet, et on peut se demander l’impact des algorithmes de recommandations. Même si ceci est notre motivation première, nous nous éloignons de ce sujet pour proposer un cadre scientifique général pour analyser la diversité. Nous trouvons que le formalisme de graphe est assez utile pour pouvoir représenter des données relationnelles. Plus précisément, nous allons analyser des données relationnelles avec des entités de différentes natures. C’est pourquoi nous avons choisi le formalisme de graphe n-partie car c’est une bonne manière de représenter une grande diversité de données. Même si nos premières données étudiées seront en lien avec les algorithmes de recommandation (consommation musicale ou achat d’article sur une plateforme) nous allons voir au fil du manuscrit en quoi ce formalisme peut être adapté à d’autres types de données (utilisateurs politisés sur Twitter, invités d’émissions de télévision, installation d’ONG dans différents États...). Il y a plusieurs objectifs dans cette étude : — Définir mathématiquement des indicateurs de diversité sur les graphes n-parties. — Définir algorithmiquement comment les calculer. — Programmer ces algorithmes pour en faire un objet informatique utilisable. — Utiliser ces programmes sur des données assez variées. — Voir les sens différents que nos indicateurs peuvent avoir. Nous commencerons par décrire le formalisme mathématique nécessaire à notre étude. Puis nous appliquerons notre objet mathématique à des exemples de base pour y voir toutes les possibilités que notre objet nous offre. Ceci nous montrera l’importance de normaliser nos indicateurs, et nous motivera à étudier une normalisation par l’aléatoire. Ensuite nous verrons une autre série d’exemples qui nous permettrons d’aller plus loin sur nos indicateurs, en dépassant le coté statique et tripartie pour aborder des graphes avec plus de couches et dépendant du temps. Pour pouvoir avoir une meilleure vision de ce que les données réelles nous apportent, nous étudierons nos indicateurs sur des graphes complètement générés aléatoirementThere is no longer any need to prove that digital technology, the Internet and the web have led to a revolution, particularly in the way people get information. Like any revolution, it is followed by a series of issues : equal treatment of users and suppliers, ecologically sustainable consumption, freedom of expression and censorship, etc. Research needs to provide a clear vision of these stakes. Among these issues, we can talk about two phenomena : the echo chamber phenomenon and the filter bubble phenomenon. These two phenomena are linked to the lack of diversity of information visible on the Internet, and one may wonder about the impact of recommendation algorithms. Even if this is our primary motivation, we are moving away from this subject to propose a general scientific framework to analyze diversity. We find that the graph formalism is useful enough to be able to represent relational data. More precisely, we will analyze relational data with entities of different natures. This is why we chose the n-part graph formalism because this is a good way to represent a great diversity of data. Even if the first data we studied is related to recommendation algorithms (music consumption or purchase of articles on a platform) we will see over the course of the manuscript how this formalism can be adapted to other types of data (politicized users on Twitter, guests of television shows, establishment of NGOs in different States ...). There are several objectives in this study : — Mathematically define diversity indicators on the n-part graphs. — Algorithmically define how to calculate them. — Program these algorithms to make them a usable computer object. — Use these programs on quite varied data. — See the different meanings that our indicators can have. We will begin by describing the mathematical formalism necessary for our study. Then we will apply our mathematical object to basic examples to see all the possibilities that our object offers us. This will show us the importance of normalizing our indicators, and will motivate us to study random normalization. Then we will see another series of examples which will allow us to go further on our indicators, going beyond the static and tripartite side to approach graphs with more layers and depending on time. To be able to have a better vision of what the real data brings us, we will study our indicators on completely randomly generated graphs
16
Axelsson, Victor. « Collaborative Recommendations for Music Session Instrumentation : Contrasting Graph to ML Based Approaches ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-232065.
Texte intégralRésumé :
Digital music composers are required to become proficient with relevant tools necessary for music in their particular domain. The learning curve for acquiring the skills for creative music composing, relative to the respective tooling, can be steep. The topic of recommendation systems aims to help the user getting over this threshold by filtering out irrelevant material. Many of the state-ofthe-art recommendation systems focus on metrics that are easy to measure as opposed to focusing on metrics that reflect a natural next-step when creating and listening to music. There is an exaggerated focus on smaller sets of metrics, especially accuracy metrics, and how these can be optimized. At the same time, there is support for the need of using complementary metrics, such as novelty and catalogue coverage, for more diversified recommendations. This suggests that even though the need for complementary metrics is known, it is often overlooked. The majority of these state-of-the-art approaches utilizes recommendations based either on graphs or machine learned models and little elaboration on how these approaches will effect the metrics are shown. The used toolset for the conducted experiment is composed of sessions with digital instruments, where the recommendation systems aims to give recommendations on what instrument to pick as the next step in the session. The contribution of this thesis includes how the architecture of the recommendation system can be composed in order to have a more fine grained control over the optimization of different metrics. By using scoring from a linear combination of similarity, selfexciting events and a weighted graph different metrics can dynamically be given more space. By contrasting this graph based approach to a machine learned model this thesis shows how metrics are effected by the architecture, so that recommendation systems can be built for better transparency and more user control over metric optimization.Vid digitalt musikskapande behöver kompositören lära sig relevanta verktyg för musik i den specifika domänen. Inlärningskurvan för anskaffningen av färdigheter för kreativt musikskapande, med avseende på tillgängliga verktyg, kan vara brant. Rekommendationssystem syftar till att hjälpa användaren komma över inlärningströskeln genom att filtrera ut relevant material. Ett gemensamt problem för de vanligare rekommendationsmetoderna är att dessa fokuserar på enkelmätt utvärderingsmetrik. Detta står i kontrast till sådan metrik vilken återspeglar ett naturligt nästa steg vid konsumtion och skapande av musik. Det finns ett överdrivet fokus på en liten grupp mätvärden, speciellt träffsäkerhet (eng. accuracy), och hur dessa kan optimeras. Samtidigt finns det också ett stort stöd för behovet av kompletterande metrik, såsom nyheter (eng. novelty) och katalogtäckning (eng. catalogue coverage), för en bättre mångfald i rekommendationerna. Detta tyder på att även om behovet av kompletterande metrik är känt, förbises det ofta. Majoriteten av de tillgängliga systemen använder rekommendationer vilka baseras antingen på grafer eller maskinlärda modeller. Vanligt förekommande är att diskussionen rörande valet av utvärderingsmetrik och metod samt dessas ömsesidiga influens bortses ifrån. De verktyg som används för experimentet i denna uppsats består av sessioner med digitala instrument, där rekommendationen syftar till att visa vilket instrument som kan väljas i nästa steg i sessionen. Denna uppsatts bidrar med en diskussion om hur datadrivna rekommendationsarkitekturer och tillvägagångssätt kan konstrueras för att erhålla en mer detaljerad kontroll över vilka mätvärden som optimeras. Genom att använda en linjär kombination av likhet, självexciterade händelser (eng. self-exciting events) och en viktad graf kan olika rekommendationsmetoder, och så till vida utvärderingsmetrik, dynamiskt ges mer utrymme i den slutgiltiga bedömningen. Genom att jämföra detta grafbaserade tillvägagångssätt med en maskinlärd modell visar denna uppsats hur metrik påverkas av metodval. Detta medför att rekommendationssystem kan konstrueras för bättre transparens för musikskaparen och mer användarkontroll över metrikoptimeringen.
17
Ruas, Olivier. « The many faces of approximation in KNN graph computation ». Thesis, Rennes 1, 2018. http://www.theses.fr/2018REN1S088/document.
Texte intégralRésumé :
La quantité incroyable de contenu disponible dans les services en ligne rend le contenu intéressant incroyablement difficile à trouver. La manière la plus emblématique d’aider les utilisateurs consiste à faire des recommandations. Le graphe des K-plus-proches-voisins (K-Nearest-Neighbours (KNN)) connecte chaque utilisateur aux k autres utilisateurs qui lui sont les plus similaires, étant donnée une fonction de similarité. Le temps de calcul d’un graphe KNN exact est prohibitif dans les services en ligne. Les approches existantes approximent l’ensemble de candidats pour chaque voisinage pour diminuer le temps de calcul. Dans cette thèse, nous poussons plus loin la notion d’approximation : nous approximons les données de chaque utilisateur, la similarité et la localité de données. L’approche obtenue est nettement plus rapide que toutes les autresThe incredible quantity of available content in online services makes content of interest incredibly difficult to find. The most emblematic way to help the users is to do item recommendation. The K-Nearest-Neighbors (KNN) graph connects each user to its k most similar other users, according to a given similarity metric. The computation time of an exact KNN graph is prohibitive in online services. Existing approaches approximate the set of candidates for each user’s neighborhood to decrease the computation time. In this thesis we push farther the notion of approximation : we approximate the data of each user, the similarity and the data locality. The resulting approach clearly outperforms all the other ones
18
Arrascue, Ayala Victor Anthony [Verfasser], et Georg [Akademischer Betreuer] Lausen. « Towards an effective consumption of large-scale knowledge graphs for recommendations ». Freiburg : Universität, 2020. http://d-nb.info/1223366189/34.
Texte intégral
19
Kaya, Hamza. « Using Social Graphs In One-class Collaborative Filtering Problem ». Master's thesis, METU, 2009. http://etd.lib.metu.edu.tr/upload/12611131/index.pdf.
Texte intégralRésumé :
One-class collaborative filtering is a special type of collaborative filtering methods that aims to deal with datasets that lack counter-examples. In this work, we introduced social networks as a new data source to the one-class collaborative filtering (OCCF) methods and sought ways to benefit from them when dealing with OCCF problems. We divided our research into two parts. In the first part, we proposed different weighting schemes based on social graphs for some well known OCCF
algorithms. One of the weighting schemes we proposed outperformed our baselines for some of the datasets we used. In the second part, we focused on the dataset differences in order to find out why our algorithm performed better on some of the datasets. We compared social graphs with the graphs of users and their neighbors generated by the k-NN algorithm. Our research showed that social graphs generated from a specialized domain better improves the recommendation performance than the social graphs generated from a more generic domain.
20
Chennupati, Nikhil. « Recommending Collaborations Using Link Prediction ». Wright State University / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=wright1621899961924795.
Texte intégral
21
De, Vos Gerhard Johannes. « Generally recognised accounting practice : a critical evaluation of the impact of grap 23 on administrative tax legislation and recommendations ». Diss., University of Pretoria, 2009. http://hdl.handle.net/2263/23893.
Texte intégralRésumé :
The application of accrual accounting principles is a challenge for public sectors internationally and increases the level of transparency and accountability of management. Taxation authorities are governed by legislation and have to be supported by a sound legislative framework to enable effective administration of taxes and the proper application of the accrual accounting principles. The recent issuing of the accounting standard for taxes and developments relating to the subsequent measurement of tax receivables highlights the ineffectiveness of current administrative tax legislation relating to penalties and interest which does not allow SARS to effectively apply accrual accounting principles. The receipt of taxpayer returns and payments as required by legislation are critical in order to allow the recording of taxes owed in the financial records of SARS. These taxpayer actions can only be effectively influenced by an effective penalty regime. Similarly, the current interest regimes on tax receivables and payables need to be adjusted in order to allow efficiencies and be comparative to market rates and calculation methods. International comparisons of penalty and interest regimes did not indicate a specific standard regime that should be applied, but the United Kingdom identified sound design principles for penalty and interest regimes. A simple standardised penalty and interest regime for all taxes administered by SARS is recommended which meets the identified design principles and supports the accrual accounting principles. The move to accrual accounting is an additional driver for administrative legislative reform which supports the effective management of taxation authorities. CopyrightDissertation (MCom)--University of Pretoria, 2009.
Taxation
unrestricted
22
Benkoussas, Chahinez. « Approches non supervisées pour la recommandation de lectures et la mise en relation automatique de contenus au sein d'une bibliothèque numérique ». Thesis, Aix-Marseille, 2016. http://www.theses.fr/2016AIXM4379/document.
Texte intégralRésumé :
Cette thèse s’inscrit dans le domaine de la recherche d’information (RI) et la recommandation de lecture. Elle a pour objets :— La création de nouvelles approches de recherche de documents utilisant des techniques de combinaison de résultats, d’agrégation de données sociales et de reformulation de requêtes ;— La création d’une approche de recommandation utilisant des méthodes de RI et les graphes entre les documents. Deux collections de documents ont été utilisées. Une collection qui provient de l’évaluation CLEF (tâche Social Book Search - SBS) et la deuxième issue du domaine des sciences humaines et sociales (OpenEdition, principalement Revues.org). La modélisation des documents de chaque collection repose sur deux types de relations :— Dans la première collection (CLEF SBS), les documents sont reliés avec des similarités calculées par Amazon qui se basent sur plusieurs facteurs (achats des utilisateurs, commentaires, votes, produits achetés ensemble, etc.) ;— Dans la deuxième collection (OpenEdition), les documents sont reliés avec des relations de citations (à partir des références bibliographiques).Le manuscrit est structuré en deux parties. La première partie «état de l’art» regroupe une introduction générale, un état de l’art sur la RI et sur les systèmes de recommandation. La deuxième partie «contributions» regroupe un chapitre sur la détection de comptes rendus de lecture au sein de la collection OpenEdition (Revues.org), un chapitre sur les méthodes de RI utilisées sur des requêtes complexes et un dernier chapitre qui traite l’approche de recommandation proposée qui se base sur les graphesThis thesis deals with the field of information retrieval and the recommendation of reading. It has for objects:— The creation of new approach of document retrieval and recommendation using techniques of combination of results, aggregation of social data and reformulation of queries;— The creation of an approach of recommendation using methods of information retrieval and graph theories.Two collections of documents were used. First one is a collection which is provided by CLEF (Social Book Search - SBS) and the second from the platforms of electronic sources in Humanities and Social Sciences OpenEdition.org (Revues.org). The modelling of the documents of every collection is based on two types of relations:— For the first collection (SBS), documents are connected with similarity calculated by Amazon which is based on several factors (purchases of the users, the comments, the votes, products bought together, etc.);— For the second collection (OpenEdition), documents are connected with relations of citations, extracted from bibliographical references.We show that the proposed approaches bring in most of the cases gain in the performances of research and recommendation. The manuscript is structured in two parts. The first part "state of the art" includes a general introduction, a state of the art of informationretrieval and recommender systems. The second part "contributions" includes a chapter on the detection of reviews of books in Revues.org; a chapter on the methods of IR used on complex queries written in natural language and last chapter which handles the proposed approach of recommendation which is based on graph
23
Gulikers, Lennart. « Sur deux problèmes d’apprentissage automatique : la détection de communautés et l’appariement adaptatif ». Thesis, Paris Sciences et Lettres (ComUE), 2017. http://www.theses.fr/2017PSLEE062/document.
Texte intégralRésumé :
Dans cette thèse, nous étudions deux problèmes d'apprentissage automatique : (I) la détection des communautés et (II) l'appariement adaptatif. I) Il est bien connu que beaucoup de réseaux ont une structure en communautés. La détection de ces communautés nous aide à comprendre et exploiter des réseaux de tout genre. Cette thèse considère principalement la détection des communautés par des méthodes spectrales utilisant des vecteurs propres associés à des matrices choisiesavec soin. Nous faisons une analyse de leur performance sur des graphes artificiels. Au lieu du modèle classique connu sous le nom de « Stochastic Block Model » (dans lequel les degrés sont homogènes) nous considérons un modèle où les degrés sont plus variables : le « Degree-Corrected Stochastic Block Model » (DC-SBM). Dans ce modèle les degrés de tous les nœuds sont pondérés - ce qui permet de générer des suites des degrés hétérogènes. Nous étudions ce modèle dans deux régimes: le régime dense et le régime « épars », ou « dilué ». Dans le régime dense, nous prouvons qu'un algorithme basé sur une matrice d'adjacence normalisée réussit à classifier correctement tous les nœuds sauf une fraction négligeable. Dans le régime épars il existe un seuil en termes de paramètres du modèle en-dessous lequel n'importe quel algorithme échoue par manque d'information. En revanche, nous prouvons qu'un algorithme utilisant la matrice « non-backtracking » réussit jusqu'au seuil - cette méthode est donc très robuste. Pour montrer cela nous caractérisons le spectre des graphes qui sont générés selon un DC-SBM dans son régime épars. Nous concluons cette partie par des tests sur des réseaux sociaux. II) Les marchés d'intermédiation en ligne tels que des plateformes de Question-Réponse et des plateformes de recrutement nécessitent un appariement basé sur une information incomplète des deux parties. Nous développons un modèle de système d'appariement entre tâches et serveurs représentant le comportement de telles plateformes. Pour ce modèle nous donnons une condition nécessaire et suffisante pour que le système puisse gérer un certain flux de tâches. Nous introduisons également une politique de « back-pressure » sous lequel le débit gérable par le système est maximal. Nous prouvons que cette politique atteint un débit strictement plus grand qu'une politique naturelle « gloutonne ». Nous concluons en validant nos résultats théoriques avec des simulations entrainées par des données de la plateforme Stack-OverflowIn this thesis, we study two problems of machine learning: (I) community detection and (II) adaptive matching. I) It is well-known that many networks exhibit a community structure. Finding those communities helps us understand and exploit general networks. In this thesis we focus on community detection using so-called spectral methods based on the eigenvectors of carefully chosen matrices. We analyse their performance on artificially generated benchmark graphs. Instead of the classical Stochastic Block Model (which does not allow for much degree-heterogeneity), we consider a Degree-Corrected Stochastic Block Model (DC-SBM) with weighted vertices, that is able to generate a wide class of degree sequences. We consider this model in both a dense and sparse regime. In the dense regime, we show that an algorithm based on a suitably normalized adjacency matrix correctly classifies all but a vanishing fraction of the nodes. In the sparse regime, we show that the availability of only a small amount of information entails the existence of an information-theoretic threshold below which no algorithm performs better than random guess. On the positive side, we show that an algorithm based on the non-backtracking matrix works all the way down to the detectability threshold in the sparse regime, showing the robustness of the algorithm. This follows after a precise characterization of the non-backtracking spectrum of sparse DC-SBM's. We further perform tests on well-known real networks. II) Online two-sided matching markets such as Q&A forums and online labour platforms critically rely on the ability to propose adequate matches based on imperfect knowledge of the two parties to be matched. We develop a model of a task / server matching system for (efficient) platform operation in the presence of such uncertainty. For this model, we give a necessary and sufficient condition for an incoming stream of tasks to be manageable by the system. We further identify a so-called back-pressure policy under which the throughput that the system can handle is optimized. We show that this policy achieves strictly larger throughput than a natural greedy policy. Finally, we validate our model and confirm our theoretical findings with experiments based on user-contributed content on an online platform
24
« Graph-based recommendation with label propagation ». 2011. http://library.cuhk.edu.hk/record=b5894820.
Texte intégralRésumé :
Wang, Dingyan.Thesis (M.Phil.)--Chinese University of Hong Kong, 2011.
Includes bibliographical references (p. 97-110).
Abstracts in English and Chinese.
Abstract --- p.ii
Acknowledgement --- p.vi
Chapter 1 --- Introduction --- p.1
Chapter 1.1 --- Overview --- p.1
Chapter 1.2 --- Motivations --- p.6
Chapter 1.3 --- Contributions --- p.9
Chapter 1.4 --- Organizations of This Thesis --- p.11
Chapter 2 --- Background --- p.14
Chapter 2.1 --- Label Propagation Learning Framework --- p.14
Chapter 2.1.1 --- Graph-based Semi-supervised Learning --- p.14
Chapter 2.1.2 --- Green's Function Learning Framework --- p.16
Chapter 2.2 --- Recommendation Methods --- p.19
Chapter 2.2.1 --- Traditional Memory-based Methods --- p.19
Chapter 2.2.2 --- Traditional Model-based Methods --- p.20
Chapter 2.2.3 --- Label Propagation Recommendation Models --- p.22
Chapter 2.2.4 --- Latent Feature Recommendation Models . --- p.24
Chapter 2.2.5 --- Social Recommendation Models --- p.25
Chapter 2.2.6 --- Tag-based Recommendation Models --- p.25
Chapter 3 --- Recommendation with Latent Features --- p.28
Chapter 3.1 --- Motivation and Contributions --- p.28
Chapter 3.2 --- Item Graph --- p.30
Chapter 3.2.1 --- Item Graph Definition --- p.30
Chapter 3.2.2 --- Item Graph Construction --- p.31
Chapter 3.3 --- Label Propagation Recommendation Model with Latent Features --- p.33
Chapter 3.3.1 --- Latent Feature Analysis --- p.33
Chapter 3.3.2 --- Probabilistic Matrix Factorization --- p.35
Chapter 3.3.3 --- Similarity Consistency Between Global and Local Views (SCGL) --- p.39
Chapter 3.3.4 --- Item-based Green's Function Recommendation Based on SCGL --- p.41
Chapter 3.4 --- Experiments --- p.41
Chapter 3.4.1 --- Dataset --- p.43
Chapter 3.4.2 --- Baseline Methods --- p.43
Chapter 3.4.3 --- Metrics --- p.45
Chapter 3.4.4 --- Experimental Procedure --- p.45
Chapter 3.4.5 --- Impact of Weight Parameter u --- p.46
Chapter 3.4.6 --- Performance Comparison --- p.48
Chapter 3.5 --- Summary --- p.50
Chapter 4 --- Recommendation with Social Network --- p.51
Chapter 4.1 --- Limitation and Contributions --- p.51
Chapter 4.2 --- A Social Recommendation Framework --- p.55
Chapter 4.2.1 --- Social Network --- p.55
Chapter 4.2.2 --- User Graph --- p.57
Chapter 4.2.3 --- Social-User Graph --- p.59
Chapter 4.3 --- Experimental Analysis --- p.60
Chapter 4.3.1 --- Dataset --- p.61
Chapter 4.3.2 --- Metrics --- p.63
Chapter 4.3.3 --- Experiment Setting --- p.64
Chapter 4.3.4 --- Impact of Control Parameter u --- p.65
Chapter 4.3.5 --- Performance Comparison --- p.67
Chapter 4.4 --- Summary --- p.69
Chapter 5 --- Recommendation with Tags --- p.71
Chapter 5.1 --- Limitation and Contributions --- p.71
Chapter 5.2 --- Tag-Based User Modeling --- p.75
Chapter 5.2.1 --- Tag Preference --- p.75
Chapter 5.2.2 --- Tag Relevance --- p.78
Chapter 5.2.3 --- User Interest Similarity --- p.80
Chapter 5.3 --- Tag-Based Label Propagation Recommendation --- p.83
Chapter 5.4 --- Experimental Analysis --- p.84
Chapter 5.4.1 --- Douban Dataset --- p.85
Chapter 5.4.2 --- Experiment Setting --- p.86
Chapter 5.4.3 --- Metrics --- p.87
Chapter 5.4.4 --- Impact of Tag and Rating --- p.88
Chapter 5.4.5 --- Performance Comparison --- p.90
Chapter 5.5 --- Summary --- p.92
Chapter 6 --- Conclusions and Future Work --- p.94
Chapter 6.0.1 --- Conclusions --- p.94
Chapter 6.0.2 --- Future Work --- p.96
Bibliography --- p.97
25
Silva, Ricardo Manuel Gonçalves da. « Knowledge Graph-Based Recipe Recommendation System ». Master's thesis, 2020. https://hdl.handle.net/10216/132659.
Texte intégral
26
Silva, Ricardo Manuel Gonçalves da. « Knowledge Graph-Based Recipe Recommendation System ». Dissertação, 2020. https://hdl.handle.net/10216/132659.
Texte intégral
27
Yang, Sheng-Fang, et 楊昇芳. « Cross-domain music recommendation based on superhighway graph embedding ». Thesis, 2019. http://ndltd.ncl.edu.tw/handle/e6h2fc.
Texte intégralRésumé :
碩士國立政治大學
資訊科學系
108
In recent years, big data and machine learning technology have been rapidly growing, and recommendation systems have been widely used in various real-world applications, such as music recommendation in music streaming services. However, for different domains, the recommneder systems will be different, because of the distinct user behavior data. Therefore, this thesis aims to use Heterogeneous Information Network Embedding to project the nodes in a network/domain into another network/domain on the basis of the low-dimension representations of the nodes. Therefore, this paper proposes a cross-domain music recommendation approach based on heterogeneous information network representation learning, the idea of which is to enrich the new domain/market data by using a well developed domain/market.
28
BHANDARI, UPASANA. « SEREDIPITIOUS RECOMMENDATION FOR MOBILE APPLICATIONS USING ITEM - SIMILARITY GRAPH ». Thesis, 2016. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14508.
Texte intégralRésumé :
Abstract
The domain of mobile applications(apps) has recently surfaced and
generated lot of interest in academia and industry alike. With an
App-store for every leading operating system - Apple, Android,
Blackberry,Windows, an explosive growth of Mobile applications is
not a surprise. The absolute number of apps currently in existence,
as well as their rates of growth, are remarkable. This might be
good news for the developers from the revenue perspective but for
consumers it means the inherent task of ”App Discovery” being
intensified.
A reasonable solution to this problem are Recommender systems.
They usually deal with indicators of user preferences(purchase history/
rating history) for suggesting/predicting items for a target user.
An e↵ective way to cut-the-queue and straightaway hit the user’s
interest in shortest possible time, RS are extremely popular with
commercial systems today.
To generate relevant recommendations for users, our system tries
to leverage the interest patterns in the downloaded applications on
mobile phones of users themselves by using item-item similarity
graphs. This work essentially tries to overcome the inherent problem
of over-specialization in content based recommender system
by using graph approach.
This thesis first presents the background literature for recommender
systems and then proposes a graph based approach for recommending
serendipitous recommendations to a user.
29
Wetzker, Robert [Verfasser]. « Graph-based recommendation in broad folksonomies / vorgelegt von Robert Wetzker ». 2010. http://d-nb.info/1005965838/34.
Texte intégral
30
Vijaikumar, M. « Neural Models for Personalized Recommendation Systems with External Information ». Thesis, 2021. https://etd.iisc.ac.in/handle/2005/5667.
Texte intégralRésumé :
Personalized recommendation systems use the data generated by user-item interactions (for example, in the form of ratings) to predict different users interests in available items and recommend a set of items or products to the users. The sparsity of data, cold start, and scalability are some of the important challenges faced by the developers of recommendation systems. These problems are alleviated by using external information, which can be in the form of a social network or a heterogeneous information network, or cross-domain knowledge. This thesis develops novel neural network models for designing personalized recommendation systems using the available external information.
The first part of the thesis studies the top-N item recommendation setting where the external information is available in the form of a social network or heterogeneous information network. Unlike a simple recommendation setting, capturing complex relationships amongst entities (users, items, and connected objects) becomes essential when a social and heterogeneous information network is available. In a social network, all socially connected users do not have equal influence on each other. Further, estimating the quantum of influence among entities in a user-item interaction network is important when only implicit ratings are available. We address these challenges by proposing a novel neural network model, SoRecGAT, which employs a multi-head and multi-layer graph attention mechanism. The attention mechanism helps the model learn the influence of entities on each other more accurately. Further, we exploit heterogeneous information networks (HIN) to gather multiple views for the items. A novel neural network model -- GAMMA (Graph and Multi-view Memory Attention mechanism) is proposed to extract relevant information from HINs. The proposed model is an end-to-end model which eliminates the need for learning a similarity matrix offline using some manually selected meta-paths before optimizing the desired objective function.
In the second part of the thesis, we focus on top-N bundle recommendation and list continuation setting. Bundle recommendation is the task of recommending a group of products instead of individual products to users. We study two interesting challenges -- (1) how to personalize and recommend existing bundles to users and (2) how to generate personalized novel bundles targeting specific users. We propose GRAM-SMOT -- a graph attention-based framework that considers higher-order relationships among the users, items, and bundles and the relative influence of items present in the bundles. For efficiently learning the embeddings of the entities, we define a loss function based on the metric-learning approach. A strategy that leverages submodular optimization ideas is used to generate novel bundles.
We also study the problem of top-N personalized list continuation where the task is to curate the next items to user-generated lists (ordered sequence of items) in a personalized way by using the sequential information of the items in the list. The main challenge in this task is understanding the ternary relationships among the users, items, and lists. We propose HyperTeNet -- a self-attention hypergraph and Transformer-based neural network architecture for the personalized list continuation task. Here, graph convolutions are used to learn the multi-hop relationship among entities of the same type. A self-attention-based hypergraph neural network is proposed to learn the ternary relationships among the interacting entities via hyperlink prediction in a 3-uniform hypergraph. Further, the entity embeddings are shared with a Transformer-based architecture and are learned through an alternating optimization procedure.
The final part of the thesis focuses on the personalized rating prediction setting where external information is available in the form of cross-domain knowledge. We propose an end-to-end neural network model, NeuCDCF, that provides a way to alleviate data sparsity problems by exploiting the information from related domains. NeuCDCF is based on a wide and deep framework and learns the representations jointly using matrix factorization and deep neural networks. We study the challenges involved in handling diversity between domains and learning complex non-linear relationships among entities within and across domains.
We conduct extensive experiments in each of these settings using several real-world datasets and demonstrate the efficacy of the proposed models.
31
Xiao, Li-Pin, et 蕭立品. « Personalized Product Recommendation Based on Embedding of Multi-Behavior Network and Product Information Knowledge Graph ». Thesis, 2019. http://ndltd.ncl.edu.tw/handle/uc79jt.
Texte intégralRésumé :
碩士國立交通大學
資訊科學與工程研究所
108
As the growth of e-commerce, people can buy almost everything they need for their trips like SIM cards, theme park tickets and transportation tickets on the internet before they head on for the trip. When users browse items and order some products on website, they may leave their implicitly preference to items. The recorded implicit feedback can provide knowledge for improving the recommendation system. However, there are two challenges for knowledge exploring from implicit feedback data. First, many of products have been browsed frequently but may not consequentially be ordered. The browsing-browsing actions are the majority compared to the browsing-order actions. The users' actions may not directly be considered as the preference on a specific item. Second, the popularity of sold products has a highly skewed distribution. The recommendation may meet the cold start problem. In this paper, we proposed a hybrid recommendation model. For extracting knowledge from implicit feedback, we develop the neighborhood structure of users and products in the multi-behavior interaction network that incorporates the browsing and order behaviors simultaneously. To deal with the cold product issue and the skewed distribution problem, we take the product information into consideration by using the metadata of products and extracting more features from the textual contents to form a knowledge graph. By applying embedding algorithms to the multi-behavior interaction network and the knowledge graph, we are able to catch the user preference from the collaborative implicit feedback aspect and product information aspect. To evaluate the performance of our model, we conduct extensive experiments on the real world dataset. The result of our approaches outperforms several widely used methods for recommendation system.
32
Hsu, Pei-Ying, et 許珮瑩. « A Novel Explainable Mutual Fund Recommendation System Based on Deep Learning Techniques with Knowledge Graph Embeddings ». Thesis, 2019. http://ndltd.ncl.edu.tw/handle/wur49w.
Texte intégralRésumé :
碩士國立交通大學
資訊管理研究所
107
Since deep learning based models have gained success in various fields during recent years, many recommendation systems also start to take advantage of the deep learning techniques. However, while the deep learning based recommendation systems have achieved high recommendation performance, the lack of interpretability may reduce users' trust and satisfaction, while limiting the model to wide adoption in the real world. As a result, to strike a balance between high accuracy and interpretability, or even obtain both of them at the same time, has become a popular issue among the researches of recommendation systems. In this thesis, we would like to predict and recommend the funds that would be purchased by the customers in the next month, while providing explanations simultaneously. To achieve the goal, we leverage the structure of knowledge graph, and take advantage of deep learning techniques to embed customers and funds features to a unified latent space. We fully utilize the structure knowledge which cannot be learned by the traditional deep learning models, and get the personalized recommendations and explanations. Moreover, we extend the explanations to more complex ones by changing the training procedure of the model, and proposed a measure to rate for the customized explanations while considering strength and uniqueness of the explanations at the same time. Finally, we regard that the knowledge graph based structure could be extended to other applications, and proposed some possible special recommendations accordingly. By evaluating on the dataset of mutual fund transaction records, we verify the effectiveness of our model to provide precise recommendations, and also evaluate the assumptions that our model could utilize the structure knowledge well. Last but not least, we conduct some case study of explanations to demonstrate the effectiveness of our model to provide usual explanations, complex explanations, and other special recommendations.
33
Peixoto, Ana Rita Henrique. « A graph-based approach for sustainable walking tour recommendations : The case of Lisbon overcrowding ». Master's thesis, 2019. http://hdl.handle.net/10071/20234.
Texte intégralRésumé :
Motivation: Mass tourism brought problems of carrying capacity in city management.
More and more tourists flock to the most famous zones, thereby causing
overcrowding situations, while other sustainable points of interest (POIs) are
under-visited.
Goal: Allow local tourism managing authorities to assemble a database of georeferenced
sustainable POIs. Then, combine the latter with local crowding data and
implement a walking tour recommender system.
Proposal: A web platform to experts adds, in an intuitive way by using a map,POIs
with sustainable data. Creating a new database of Lisbon (case of study) sustainable
POIs. Implement a tour generator graph-algorithm that receives: user preferences,
tour constraints, sustainable POIs and crowd data. Providing a customize
tour, that obeys the domain constraints, suggests sustainable POIs and avoids the
more crowded areas. Solving a multicriteria shortest path problem.
Conclusion: Evidence is provided on the feasibility of computing walking tour recommendations,
meeting multiple and complex constraints, namely by promoting
sustainability and mitigating crowding, using a graph search algorithm.Motivação: O turismo em massa trouxe problemas de controlo da capacidade de carga na gestão das cidades. Os turistas, em número crescente, aglomeram-se nas zonas mais famosas, causando aí situações de sobrelotação, enquanto outros pontos de interesse (POIs, em Inglês) sustentáveis são sub-visitados. Objetivo: Permitir que as autoridades gestoras do turismo local montem uma base de dados de POIs sustentáveis, georreferenciados. Em seguida, combinar estes últimos com os dados de aglomeração local e implementar um sistema de recomendação de passeios turísticos pedestres. Proposta: Uma plataforma web para que o especialistas adicionem, de forma intuitiva através de um mapa, os pontos de interesse sustentáveis. Implementar um algoritmo de grafos, que gera caminhos e que recebe: as preferências do utilizador, as restrições do domínio do caminho, pontos de interesse sustentáveis e dados de congestionamento. Fornecendo assim, um caminho personalizado que obdece às restrições, sugere pontos de interesse sustentáveis e evita as áreas mais movimentadas. Deste modo, resolve o problema do caminho mais curto com multicriterias. Conclusão: São fornecidas evidências sobre a viabilidade de computar recomendações de passeios turísticos a pé, atendendo a restrições múltiplas e complexas, nomeadamente promovendo a sustentabilidade e mitigando a superlotação, usando um algoritmo de pesquisa em grafos.
34
Salamat, Amirreza. « Heterogeneous Graph Based Neural Network for Social Recommendations with Balanced Random Walk Initialization ». Thesis, 2020. http://hdl.handle.net/1805/24769.
Texte intégralRésumé :
Indiana University-Purdue University Indianapolis (IUPUI)Research on social networks and understanding the interactions of the users can be modeled as a task of graph mining, such as predicting nodes and edges in networks. Dealing with such unstructured data in large social networks has been a challenge for researchers in several years. Neural Networks have recently proven very successful in performing predictions on number of speech, image, and text data and have become the de facto method when dealing with such data in a large volume. Graph NeuralNetworks, however, have only recently become mature enough to be used in real large-scale graph prediction tasks, and require proper structure and data modeling to be viable and successful. In this research, we provide a new modeling of the social network which captures the attributes of the nodes from various dimensions. We also introduce the Neural Network architecture that is required for optimally utilizing the new data structure. Finally, in order to provide a hot-start for our model, we initialize the weights of the neural network using a pre-trained graph embedding method. We have also developed a new graph embedding algorithm. We will first explain how previous graph embedding methods are not optimal for all types of graphs, and then provide a solution on how to combat those limitations and come up with a new graph embedding method.
35
Ding, Shichang. « User Attribute Inference via Mining User-Generated Data ». Doctoral thesis, 2020. http://hdl.handle.net/21.11130/00-1735-0000-0005-150E-5.
Texte intégral
36
(9740444), Amirreza Salamat. « Heterogeneous Graph Based Neural Network for Social Recommendations with Balanced Random Walk Initialization ». Thesis, 2021.
Trouver le texte intégralRésumé :
Research on social networks and understanding the interactions of the users can be modeled as a task of graph mining, such as predicting nodes and edges in networks.Dealing with such unstructured data in large social networks has been a challenge for researchers in several years. Neural Networks have recently proven very successful in performing predictions on number of speech, image, and text data and have become the de facto method when dealing with such data in a large volume. Graph NeuralNetworks, however, have only recently become mature enough to be used in real large-scale graph prediction tasks, and require proper structure and data modeling to be viable and successful. In this research, we provide a new modeling of the social network which captures the attributes of the nodes from various dimensions. We also introduce the Neural Network architecture that is required for optimally utilizing the new data structure. Finally, in order to provide a hot-start for our model, we initialize the weights of the neural network using a pre-trained graph embedding method. We have also developed a new graph embedding algorithm. We will first explain how previous graph embedding methods are not optimal for all types of graphs, and then provide a solution on how to combat those limitations and come up with a new graph embedding method.
37
Golovin, Nick, et Erhard Rahm. « Automatic Optimization of Web Recommendations Using Feedback and Ontology Graphs ». 2005. https://ul.qucosa.de/id/qucosa%3A32785.
Texte intégralRésumé :
Web recommendation systems have become a popular means to im-prove the usability of web sites. This paper describes the architecture of a rule-based recommendation system and presents its evaluation on two real-life ap-plications. The architecture combines recommendations from different algo-rithms in a recommendation database and applies feedback-based machine learning to optimize the selection of the presented recommendations. The rec-ommendations database also stores ontology graphs, which are used to semanti-cally enrich the recommendations. We describe the general architecture of the system and the test setting, illustrate the application of several optimization ap-proaches and present comparative results.
38
ZHANG, LI-WEI, et 張立偉. « Developed a system model program for recommendation of fertilizer application in grape ». Thesis, 1990. http://ndltd.ncl.edu.tw/handle/19528335078346005081.
Texte intégral
39
Chen, Cheng. « Trustworthiness, diversity and inference in recommendation systems ». Thesis, 2016. http://hdl.handle.net/1828/7576.
Texte intégralRésumé :
Recommendation systems are information filtering systems that help users effectively and efficiently explore large amount of information and identify items of interest. Accurate predictions of users' interests improve user satisfaction and are beneficial to business or service providers. Researchers have been making tremendous efforts to improve the accuracy of recommendations. Emerging trends of technologies and application scenarios, however, lead to challenges other than accuracy for recommendation systems. Three new challenges include: (1) opinion spam results in untrustworthy content and makes recommendations deceptive; (2) users prefer diversified content; (3) in some applications user behavior data may not be available to infer users' preference.
This thesis tackles the above challenges. We identify features of untrustworthy commercial campaigns on a question and answer website, and adopt machine learning-based techniques to implement an adaptive detection system which automatically detects commercial campaigns. We incorporate diversity requirements into a classic theoretical model and develop efficient algorithms with performance guarantees. We propose a novel and robust approach to infer user preference profile from recommendations using copula models. The proposed approach can offer in-depth business intelligence for physical stores that depend on Wi-Fi hotspots for mobile advertisement.Graduate
0984
cchenv@uvic.ca
40
SZCZERBAK, Michal. « Sensibilité aux situations de façon collaborative ». Phd thesis, 2013. http://tel.archives-ouvertes.fr/tel-00910927.
Texte intégralRésumé :
Situation awareness and collective intelligence are two technologies used in smart systems. The former renders those systems able to reason upon their abstract knowledge of what is going on. The latter enables them learning and deriving new information from a composition of experiences of their users. In this dissertation we present a doctoral research on an attempt to combine the two in order to obtain, in a collaborative fashion, situation-based rules that the whole community of entities would benefit of sharing. We introduce the KRAMER recommendation system, which we designed and implemented as a solution to the problem of not having decision support tools both situation-aware and collaborative. The system is independent from any domain of application in particular, in other words generic, and we apply its prototype implementation to context-enriched social communication scenario.