Journal articles on the topic 'Representation space / Latent space'
To see the other types of publications on this topic, follow the link: Representation space / Latent space.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Representation space / Latent space.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Gat, Itai, Guy Lorberbom, Idan Schwartz, and Tamir Hazan. "Latent Space Explanation by Intervention." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 679–87. http://dx.doi.org/10.1609/aaai.v36i1.19948.
Abstract:
The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives prediction. This study aims to reveal hidden concepts by employing an intervention mechanism that shifts the predicted class based on discrete variational autoencoders. An explanatory model then visualizes the encoded information from any hidden layer and its corresponding intervened representation. By the assessment of differences between the original representation and the intervened representation, one can determine the concepts that can alter the class, hence providing interpretability. We demonstrate the effectiveness of our approach on CelebA, where we show various visualizations for bias in the data and suggest different interventions to reveal and change bias.
2
Huang, Yulei, Ziping Ma, Huirong Li, and Jingyu Wang. "Dual Space Latent Representation Learning for Image Representation." Mathematics 11, no. 11 (May 31, 2023): 2526. http://dx.doi.org/10.3390/math11112526.
Abstract:
Semi-supervised non-negative matrix factorization (NMF) has achieved successful results due to the significant ability of image recognition by a small quantity of labeled information. However, there still exist problems to be solved such as the interconnection information not being fully explored and the inevitable mixed noise in the data, which deteriorates the performance of these methods. To circumvent this problem, we propose a novel semi-supervised method named DLRGNMF. Firstly, dual latent space is characterized by the affinity matrix to explicitly reflect the interrelationship between data instances and feature variables, which can exploit the global interconnection information in dual space and reduce the adverse impacts caused by noise and redundant information. Secondly, we embed the manifold regularization mechanism in the dual graph to steadily retain the local manifold structure of dual space. Moreover, the sparsity and the biorthogonal condition are integrated to constrain matrix factorization, which can greatly improve the algorithm’s accuracy and robustness. Lastly, an effective alternating iterative updating method is proposed, and the model is optimized. Empirical evaluation on nine benchmark datasets demonstrates that DLRGNMF is more effective than competitive methods.
3
Jin Dai, Jin Dai, and Zhifang Zheng Jin Dai. "Disentangling Representation of Variational Autoencoders Based on Cloud Models." 電腦學刊 34, no. 6 (December 2023): 001–14. http://dx.doi.org/10.53106/199115992023123406001.
Abstract:
<p>Variational autoencoder (VAE) has the problem of uninterpretable data generation process, because the features contained in the VAE latent space are coupled with each other and no mapping from the latent space to the semantic space is established. However, most existing algorithms cannot understand the data distribution features in the latent space semantically. In this paper, we propose a cloud model-based method for disentangling semantic features in VAE latent space by adding support vector machines (SVM) to feature transformations of latent variables, and we propose to use the cloud model to measure the degree of disentangling of semantic features in the latent space. The experimental results on the CelebA dataset show that the method obtains a good disentangling effect of semantic features in the latent space, which proves the effectiveness of the method from both qualitative and quantitative aspects.</p> <p> </p>
4
Namatēvs, Ivars, Artūrs Ņikuļins, Anda Slaidiņa, Laura Neimane, Oskars Radziņš, and Kaspars Sudars. "Towards Explainability of the Latent Space by Disentangled Representation Learning." Information Technology and Management Science 26 (November 30, 2023): 41–48. http://dx.doi.org/10.7250/itms-2023-0006.
Abstract:
Deep neural networks are widely used in computer vision for image classification, segmentation and generation. They are also often criticised as “black boxes” because their decision-making process is often not interpretable by humans. However, learning explainable representations that explicitly disentangle the underlying mechanisms that structure observational data is still a challenge. To further explore the latent space and achieve generic processing, we propose a pipeline for discovering the explainable directions in the latent space of generative models. Since the latent space contains semantically meaningful directions and can be explained, we propose a pipeline to fully resolve the representation of the latent space. It consists of a Dirichlet encoder, conditional deterministic diffusion, a group-swap and a latent traversal module. We believe that this study provides an insight into the advancement of research explaining the disentanglement of neural networks in the community.
5
Toledo-Marín, J. Quetzalcóatl, and James A. Glazier. "Using deep LSD to build operators in GANs latent space with meaning in real space." PLOS ONE 18, no. 6 (June 29, 2023): e0287736. http://dx.doi.org/10.1371/journal.pone.0287736.
Abstract:
Generative models rely on the idea that data can be represented in terms of latent variables which are uncorrelated by definition. Lack of correlation among the latent variable support is important because it suggests that the latent-space manifold is simpler to understand and manipulate than the real-space representation. Many types of generative model are used in deep learning, e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs). Based on the idea that the latent space behaves like a vector space Radford et al. (2015), we ask whether we can expand the latent space representation of our data elements in terms of an orthonormal basis set. Here we propose a method to build a set of linearly independent vectors in the latent space of a trained GAN, which we call quasi-eigenvectors. These quasi-eigenvectors have two key properties: i) They span the latent space, ii) A set of these quasi-eigenvectors map to each of the labeled features one-to-one. We show that in the case of the MNIST image data set, while the number of dimensions in latent space is large by design, 98% of the data in real space map to a sub-domain of latent space of dimensionality equal to the number of labels. We then show how the quasi-eigenvectors can be used for Latent Spectral Decomposition (LSD). We apply LSD to denoise MNIST images. Finally, using the quasi-eigenvectors, we construct rotation matrices in latent space which map to feature transformations in real space. Overall, from quasi-eigenvectors we gain insight regarding the latent space topology.
6
Sang, Neil. "Does Time Smoothen Space? Implications for Space-Time Representation." ISPRS International Journal of Geo-Information 12, no. 3 (March 9, 2023): 119. http://dx.doi.org/10.3390/ijgi12030119.
Abstract:
The continuous nature of space and time is a fundamental tenet of many scientific endeavors. That digital representation imposes granularity is well recognized, but whether it is possible to address space completely remains unanswered. This paper argues Hales’ proof of Kepler’s conjecture on the packing of hard spheres suggests the answer to be “no”, providing examples of why this matters in GIS generally and considering implications for spatio-temporal GIS in particular. It seeks to resolve the dichotomy between continuous and granular space by showing how a continuous space may be emergent over a random graph. However, the projection of this latent space into 3D/4D imposes granularity. Perhaps surprisingly, representing space and time as locally conjugate may be key to addressing a “smooth” spatial continuum. This insight leads to the suggestion of Face Centered Cubic Packing as a space-time topology but also raises further questions for spatio-temporal representation.
7
Heese, Raoul, Jochen Schmid, Michał Walczak, and Michael Bortz. "Calibrated simplex-mapping classification." PLOS ONE 18, no. 1 (January 17, 2023): e0279876. http://dx.doi.org/10.1371/journal.pone.0279876.
Abstract:
We propose a novel methodology for general multi-class classification in arbitrary feature spaces, which results in a potentially well-calibrated classifier. Calibrated classifiers are important in many applications because, in addition to the prediction of mere class labels, they also yield a confidence level for each of their predictions. In essence, the training of our classifier proceeds in two steps. In a first step, the training data is represented in a latent space whose geometry is induced by a regular (n − 1)-dimensional simplex, n being the number of classes. We design this representation in such a way that it well reflects the feature space distances of the datapoints to their own- and foreign-class neighbors. In a second step, the latent space representation of the training data is extended to the whole feature space by fitting a regression model to the transformed data. With this latent-space representation, our calibrated classifier is readily defined. We rigorously establish its core theoretical properties and benchmark its prediction and calibration properties by means of various synthetic and real-world data sets from different application domains.
8
You, Cong-Zhe, Vasile Palade, and Xiao-Jun Wu. "Robust structure low-rank representation in latent space." Engineering Applications of Artificial Intelligence 77 (January 2019): 117–24. http://dx.doi.org/10.1016/j.engappai.2018.09.008.
9
Banyay, Gregory A., and Andrew S. Wixom. "Latent space representation method for structural acoustic assessments." Journal of the Acoustical Society of America 155, no. 3_Supplement (March 1, 2024): A141. http://dx.doi.org/10.1121/10.0027092.
Abstract:
When targeting structural acoustic objectives, engineering practitioners face epistemic uncertainties in the selection of optimal geometries and material distributions, particularly during early stages of the design process. Models built for simulating acoustic phenomena generally produce vector-valued output quantities of interest, such as autospectral density and frequency response functions. Given finite compute resources and time we seek computationally parsimonious ways to distill meaningful design information into actionable results from a limited set of model runs, and thus aim to use machine learning to perform model order reduction. Unlike time series data for which recurrent neural networks can learn from prior time steps to inform subsequent steps, frequency-dependent data demands a different machine learning paradigm. We thus evaluate the utility of autoencoders to represent structural acoustic results with a low dimensional latent space to enable such objectives as surrogate modeling for design optimization. We demonstrate the accuracy of autoencoder based methods of constructing a manifold representation for frequency dependent functions of varying modal density and damping, and discuss the predictive capability thereof.
10
Shrivastava, Aditya Divyakant, and Douglas B. Kell. "FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space." Molecules 26, no. 7 (April 3, 2021): 2065. http://dx.doi.org/10.3390/molecules26072065.
Abstract:
The question of molecular similarity is core in cheminformatics and is usually assessed via a pairwise comparison based on vectors of properties or molecular fingerprints. We recently exploited variational autoencoders to embed 6M molecules in a chemical space, such that their (Euclidean) distance within the latent space so formed could be assessed within the framework of the entire molecular set. However, the standard objective function used did not seek to manipulate the latent space so as to cluster the molecules based on any perceived similarity. Using a set of some 160,000 molecules of biological relevance, we here bring together three modern elements of deep learning to create a novel and disentangled latent space, viz transformers, contrastive learning, and an embedded autoencoder. The effective dimensionality of the latent space was varied such that clear separation of individual types of molecules could be observed within individual dimensions of the latent space. The capacity of the network was such that many dimensions were not populated at all. As before, we assessed the utility of the representation by comparing clozapine with its near neighbors, and we also did the same for various antibiotics related to flucloxacillin. Transformers, especially when as here coupled with contrastive learning, effectively provide one-shot learning and lead to a successful and disentangled representation of molecular latent spaces that at once uses the entire training set in their construction while allowing “similar” molecules to cluster together in an effective and interpretable way.
11
Chen, Man-Sheng, Ling Huang, Chang-Dong Wang, and Dong Huang. "Multi-View Clustering in Latent Embedding Space." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3513–20. http://dx.doi.org/10.1609/aaai.v34i04.5756.
Abstract:
Previous multi-view clustering algorithms mostly partition the multi-view data in their original feature space, the efficacy of which heavily and implicitly relies on the quality of the original feature presentation. In light of this, this paper proposes a novel approach termed Multi-view Clustering in Latent Embedding Space (MCLES), which is able to cluster the multi-view data in a learned latent embedding space while simultaneously learning the global structure and the cluster indicator matrix in a unified optimization framework. Specifically, in our framework, a latent embedding representation is firstly discovered which can effectively exploit the complementary information from different views. The global structure learning is then performed based on the learned latent embedding representation. Further, the cluster indicator matrix can be acquired directly with the learned global structure. An alternating optimization scheme is introduced to solve the optimization problem. Extensive experiments conducted on several real-world multi-view datasets have demonstrated the superiority of our approach.
12
ASEERVATHAM, SUJEEVAN. "A CONCEPT VECTOR SPACE MODEL FOR SEMANTIC KERNELS." International Journal on Artificial Intelligence Tools 18, no. 02 (April 2009): 239–72. http://dx.doi.org/10.1142/s0218213009000123.
Abstract:
Kernels are widely used in Natural Language Processing as similarity measures within inner-product based learning methods like the Support Vector Machine. The Vector Space Model (VSM) is extensively used for the spatial representation of the documents. However, it is purely a statistical representation. In this paper, we present a Concept Vector Space Model (CVSM) representation which uses linguistic prior knowledge to capture the meanings of the documents. We also propose a linear kernel and a latent kernel for this space. The linear kernel takes advantage of the linguistic concepts whereas the latent kernel combines statistical and linguistic concepts. Indeed, the latter kernel uses latent concepts extracted by the Latent Semantic Analysis (LSA) in the CVSM. The kernels were evaluated on a text categorization task in the biomedical domain. The Ohsumed corpus, well known for being difficult to categorize, was used. The results have shown that the CVSM improves performance compared to the VSM.
13
Iraki, Tarek, and Norbert Link. "Generative models for capturing and exploiting the influence of process conditions on process curves." Journal of Intelligent Manufacturing 33, no. 2 (October 7, 2021): 473–92. http://dx.doi.org/10.1007/s10845-021-01846-4.
Abstract:
AbstractVariations of dedicated process conditions (such as workpiece and tool properties) yield different process state evolutions, which are reflected by different time series of the observable quantities (process curves). A novel method is presented, which firstly allows to extract the statistical influence of these conditions on the process curves and its representation via generative models, and secondly represents their influence on the ensemble of curves by transformations of the representation space. A latent variable space is derived from sampled process data, which represents the curves with only few features. Generative models are formed based on conditional propability functions estimated in this space. Furthermore, the influence of conditions on the ensemble of process curves is represented by estimated transformations of the feature space, which map the process curve densities with different conditions on each other. The latent space is formed via Multi-Task-Learning of an auto-encoder and condition-detectors. The latter classifies the latent space representations of the process curves into the considered conditions. The Bayes framework and the Multi-task Learning models are used to obtain the process curve probabilty densities from the latent space densities. The methods are shown to reveal and represent the influence of combinations of workpiece and tool properties on resistance spot welding process curves.
14
Zheng, Chuankun, Ruzhang Zheng, Rui Wang, Shuang Zhao, and Hujun Bao. "A Compact Representation of Measured BRDFs Using Neural Processes." ACM Transactions on Graphics 41, no. 2 (April 30, 2022): 1–15. http://dx.doi.org/10.1145/3490385.
Abstract:
In this article, we introduce a compact representation for measured BRDFs by leveraging Neural Processes (NPs). Unlike prior methods that express those BRDFs as discrete high-dimensional matrices or tensors, our technique considers measured BRDFs as continuous functions and works in corresponding function spaces . Specifically, provided the evaluations of a set of BRDFs, such as ones in MERL and EPFL datasets, our method learns a low-dimensional latent space as well as a few neural networks to encode and decode these measured BRDFs or new BRDFs into and from this space in a non-linear fashion. Leveraging this latent space and the flexibility offered by the NPs formulation, our encoded BRDFs are highly compact and offer a level of accuracy better than prior methods. We demonstrate the practical usefulness of our approach via two important applications, BRDF compression and editing. Additionally, we design two alternative post-trained decoders to, respectively, achieve better compression ratio for individual BRDFs and enable importance sampling of BRDFs.
15
Asai, Masataro, Hiroshi Kajino, Alex Fukunaga, and Christian Muise. "Classical Planning in Deep Latent Space." Journal of Artificial Intelligence Research 74 (August 9, 2022): 1599–686. http://dx.doi.org/10.1613/jair.1.13768.
Abstract:
Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose Latplan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), Latplan learns a complete propositional PDDL action model of the environment. Later, when a pair of images representing the initial and the goal states (planning inputs) is given, Latplan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. We evaluate Latplan using image-based versions of 6 planning domains: 8-puzzle, 15-Puzzle, Blocksworld, Sokoban and Two variations of LightsOut.
16
Shang, Ronghua, Lujuan Wang, Fanhua Shang, Licheng Jiao, and Yangyang Li. "Dual space latent representation learning for unsupervised feature selection." Pattern Recognition 114 (June 2021): 107873. http://dx.doi.org/10.1016/j.patcog.2021.107873.
17
周, 翊航. "Low-Rank Representation Algorithm Based on Latent Feature Space." Computer Science and Application 11, no. 04 (2021): 1140–48. http://dx.doi.org/10.12677/csa.2021.114117.
18
Tan, Zhen, Xiang Zhao, Yang Fang, Bin Ge, and Weidong Xiao. "Knowledge Graph Representation via Similarity-Based Embedding." Scientific Programming 2018 (July 15, 2018): 1–12. http://dx.doi.org/10.1155/2018/6325635.
Abstract:
Knowledge graph, a typical multi-relational structure, includes large-scale facts of the world, yet it is still far away from completeness. Knowledge graph embedding, as a representation method, constructs a low-dimensional and continuous space to describe the latent semantic information and predict the missing facts. Among various solutions, almost all embedding models have high time and memory-space complexities and, hence, are difficult to apply to large-scale knowledge graphs. Some other embedding models, such as TransE and DistMult, although with lower complexity, ignore inherent features and only use correlations between different entities to represent the features of each entity. To overcome these shortcomings, we present a novel low-complexity embedding model, namely, SimE-ER, to calculate the similarity of entities in independent and associated spaces. In SimE-ER, each entity (relation) is described as two parts. The entity (relation) features in independent space are represented by the features entity (relation) intrinsically owns and, in associated space, the entity (relation) features are expressed by the entity (relation) features they connect. And the similarity between the embeddings of the same entities in different representation spaces is high. In experiments, we evaluate our model with two typical tasks: entity prediction and relation prediction. Compared with the state-of-the-art models, our experimental results demonstrate that SimE-ER outperforms existing competitors and has low time and memory-space complexities.
19
Bae, Seho, Nizam Ud Din, Hyunkyu Park, and Juneho Yi. "Exploiting an Intermediate Latent Space between Photo and Sketch for Face Photo-Sketch Recognition." Sensors 22, no. 19 (September 26, 2022): 7299. http://dx.doi.org/10.3390/s22197299.
Abstract:
The photo-sketch matching problem is challenging because the modality gap between a photo and a sketch is very large. This work features a novel approach to the use of an intermediate latent space between the two modalities that circumvents the problem of modality gap for face photo-sketch recognition. To set up a stable homogenous latent space between a photo and a sketch that is effective for matching, we utilize a bidirectional (photo → sketch and sketch → photo) collaborative synthesis network and equip the latent space with rich representation power. To provide rich representation power, we employ StyleGAN architectures, such as StyleGAN and StyleGAN2. The proposed latent space equipped with rich representation power enables us to conduct accurate matching because we can effectively align the distributions of the two modalities in the latent space. In addition, to resolve the problem of insufficient paired photo/sketch samples for training, we introduce a three-step training scheme. Extensive evaluation on a public composite face sketch database confirms superior performance of the proposed approach compared to existing state-of-the-art methods. The proposed methodology can be employed in matching other modality pairs.
20
Kim, Jaein, Juwon Lee, Ungjin Jang, Seri Lee, and Jooyoung Park. "PyTorch/Pyro Implementation for Representation of Motion in Latent Space." Journal of Korean Institute of Intelligent Systems 28, no. 6 (December 31, 2018): 558–63. http://dx.doi.org/10.5391/jkiis.2018.28.6.558.
21
Kirchoff, Kathryn E., Travis Maxfield, Alexander Tropsha, and Shawn M. Gomez. "SALSA: Semantically-Aware Latent Space Autoencoder." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 12 (March 24, 2024): 13211–19. http://dx.doi.org/10.1609/aaai.v38i12.29221.
Abstract:
In deep learning for drug discovery, molecular representations are often based on sequences, known as SMILES, which allow for straightforward implementation of natural language processing methodologies, one being the sequence-to-sequence autoencoder. However, we observe that training an autoencoder solely on SMILES is insufficient to learn molecular representations that are semantically meaningful, where semantics are specified by the structural (graph-to-graph) similarities between molecules. We demonstrate by example that SMILES-based autoencoders may map structurally similar molecules to distant codes, resulting in an incoherent latent space that does not necessarily respect the semantic similarities between molecules. To address this shortcoming we propose Semantically-Aware Latent Space Autoencoder (SALSA) for molecular representations: a SMILES-based transformer autoencoder modified with a contrastive task aimed at learning graph-to-graph similarities between molecules. To accomplish this, we develop a novel dataset comprised of sets of structurally similar molecules and opt for a supervised contrastive loss that is able to incorporate full sets of positive samples. We evaluate semantic awareness of SALSA representations by comparing to its ablated counterparts, and show empirically that SALSA learns representations that maintain 1) structural awareness, 2) physicochemical awareness, 3) biological awareness, and 4) semantic continuity.
22
Wu, Xiang, Huaibo Huang, Vishal M. Patel, Ran He, and Zhenan Sun. "Disentangled Variational Representation for Heterogeneous Face Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9005–12. http://dx.doi.org/10.1609/aaai.v33i01.33019005.
Abstract:
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms. Existing approaches attempt to tackle this problem by either synthesizing visible faces from NIR faces, extracting domain-invariant features from these modalities, or projecting heterogeneous data onto a common latent space for cross-modal matching. In this paper, we take a different approach in which we make use of the Disentangled Variational Representation (DVR) for crossmodal matching. First, we model a face representation with an intrinsic identity information and its within-person variations. By exploring the disentangled latent variable space, a variational lower bound is employed to optimize the approximate posterior for NIR and VIS representations. Second, aiming at obtaining more compact and discriminative disentangled latent space, we impose a minimization of the identity information for the same subject and a relaxed correlation alignment constraint between the NIR and VIS modality variations. An alternative optimization scheme is proposed for the disentangled variational representation part and the heterogeneous face recognition network part. The mutual promotion between these two parts effectively reduces the NIR and VIS domain discrepancy and alleviates over-fitting. Extensive experiments on three challenging NIR-VIS heterogeneous face recognition databases demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods.
23
Raja, Vinayak, and Bhuvi Chopra. "Fostering Privacy in Collaborative Data Sharing via Auto-encoder Latent Space Embedding." Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023 4, no. 1 (May 13, 2024): 152–62. http://dx.doi.org/10.60087/jaigs.v4i1.129.
Abstract:
Securing privacy in machine learning via collaborative data sharing is essential for organizations seeking to harness collective data while upholding confidentiality. This becomes especially vital when protecting sensitive information across the entire machine learning pipeline, from model training to inference. This paper presents an innovative framework utilizing Representation Learning via autoencoders to generate privacy-preserving embedded data. As a result, organizations can distribute these representations, enhancing the performance of machine learning models in situations where multiple data sources converge for a unified predictive task downstream.
24
Raja, Vinayak, and BHUVI chopra. "Cultivating Privacy in Collaborative Data Sharing through Auto-encoder Latent Space Embeddings." Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023 3, no. 1 (March 30, 2024): 269–83. http://dx.doi.org/10.60087/jaigs.vol03.issue01.p283.
Abstract:
Ensuring privacy in machine learning through collaborative data sharing is imperative for organizations aiming to leverage collective data without compromising confidentiality. This becomes particularly crucial when sensitive information must be safeguarded throughout the entire machine learning process, spanning from model training to inference. This paper introduces a novel framework employing Representation Learning through autoencoders to produce privacy-preserving embedded data. Consequently, organizations can share these representations, fostering improved performance of machine learning models in scenarios involving multiple data sources for a unified predictive task downstream.
25
Raja, Vinayak, and Bhuvi Chopra. "Cultivating Privacy in Collaborative Data Sharing through Auto-encoder Latent Space Embeddings." Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023 3, no. 1 (March 30, 2024): 371–91. http://dx.doi.org/10.60087/jaigs.v3i1.126.
Abstract:
Ensuring privacy in machine learning through collaborative data sharing is imperative for organizations aiming to leverage collective data without compromising confidentiality. This becomes particularly crucial when sensitive information must be safeguarded throughout the entire machine learning process, spanning from model training to inference. This paper introduces a novel framework employing Representation Learning through autoencoders to produce privacy-preserving embedded data. Consequently, organizations can share these representations, fostering improved performance of machine learning models in scenarios involving multiple data sources for a unified predictive task downstream.
26
Liao, Jiayu, Xiaolan Liu, and Mengying Xie. "Inductive Latent Space Sparse and Low-rank Subspace Clustering Algorithm." Journal of Physics: Conference Series 2224, no. 1 (April 1, 2022): 012124. http://dx.doi.org/10.1088/1742-6596/2224/1/012124.
Abstract:
Abstract Sparse subspace clustering (SSC) and low-rank representation (LRR) are the most popular algorithms for subspace clustering. However, SSC and LRR are transductive methods and cannot deal with the new data not involved in the training data. When a new data comes, SSC and LRR need to calculate over all the data again, which is a time-consuming thing. On the other hand, for high-dimensional data, dimensionality reduction is firstly performed before running SSC and LRR algorithms which isolate the dimensionality reduction and the following subspace clustering. To overcome these shortcomings, in this paper, two sparse and low-rank subspace clustering algorithms based on simultaneously dimensionality reduction and subspace clustering which can deal with out-of-sample data were proposed. The proposed algorithms divide the whole data set into in-sample data and out-of-sample data. The in-sample data are used to learn the projection matrix and the sparse or low-rank representation matrix in the low-dimensional space. The membership of in-sample data is obtained by spectral clustering. In the low dimensional embedding space, the membership of out of sample data is obtained by collaborative representation classification (CRC). Experimental results on a variety of data sets verify that our proposed algorithms can handle new data in an efficient way.
27
Karimi Mamaghan, Amir Mohammad, Andrea Dittadi, Stefan Bauer, Karl Henrik Johansson, and Francesco Quinzan. "Diffusion-Based Causal Representation Learning." Entropy 26, no. 7 (June 28, 2024): 556. http://dx.doi.org/10.3390/e26070556.
Abstract:
Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause–effect estimation and the identification of efficient and safe interventions. However, learning causal representations remains a major challenge, due to the complexity of many real-world systems. Previous works on causal representation learning have mostly focused on Variational Auto-Encoders (VAEs). These methods only provide representations from a point estimate, and they are less effective at handling high dimensions. To overcome these problems, we propose a Diffusion-based Causal Representation Learning (DCRL) framework which uses diffusion-based representations for causal discovery in the latent space. DCRL provides access to both single-dimensional and infinite-dimensional latent codes, which encode different levels of information. In a first proof of principle, we investigate the use of DCRL for causal representation learning in a weakly supervised setting. We further demonstrate experimentally that this approach performs comparably well in identifying the latent causal structure and causal variables.
28
Winter, Robin, Floriane Montanari, Andreas Steffen, Hans Briem, Frank Noé, and Djork-Arné Clevert. "Efficient multi-objective molecular optimization in a continuous latent space." Chemical Science 10, no. 34 (2019): 8016–24. http://dx.doi.org/10.1039/c9sc01928f.
Abstract:
We utilize Particle Swarm Optimization to optimize molecules in a machine-learned continuous chemical representation with respect to multiple objectives such as biological activity, structural constrains or ADMET properties.
29
Rivero, Daniel, Iván Ramírez-Morales, Enrique Fernandez-Blanco, Norberto Ezquerra, and Alejandro Pazos. "Classical Music Prediction and Composition by Means of Variational Autoencoders." Applied Sciences 10, no. 9 (April 27, 2020): 3053. http://dx.doi.org/10.3390/app10093053.
Abstract:
This paper proposes a new model for music prediction based on Variational Autoencoders (VAEs). In this work, VAEs are used in a novel way to address two different issues: music representation into the latent space, and using this representation to make predictions of the future note events of the musical piece. This approach was trained with different songs of Handel. As a result, the system can represent the music in the latent space, and make accurate predictions. Therefore, the system can be used to compose new music either from an existing piece or from a random starting point. An additional feature of this system is that a small dataset was used for training. However, results show that the system is able to return accurate representations and predictions on unseen data.
30
Ahmed, Taufique, and Luca Longo. "Interpreting Disentangled Representations of Person-Specific Convolutional Variational Autoencoders of Spatially Preserving EEG Topographic Maps via Clustering and Visual Plausibility." Information 14, no. 9 (September 4, 2023): 489. http://dx.doi.org/10.3390/info14090489.
Abstract:
Dimensionality reduction and producing simple representations of electroencephalography (EEG) signals are challenging problems. Variational autoencoders (VAEs) have been employed for EEG data creation, augmentation, and automatic feature extraction. In most of the studies, VAE latent space interpretation is used to detect only the out-of-order distribution latent variable for anomaly detection. However, the interpretation and visualisation of all latent space components disclose information about how the model arrives at its conclusion. The main contribution of this study is interpreting the disentangled representation of VAE by activating only one latent component at a time, whereas the values for the remaining components are set to zero because it is the mean of the distribution. The results show that CNN-VAE works well, as indicated by matrices such as SSIM, MSE, MAE, and MAPE, along with SNR and correlation coefficient values throughout the architecture’s input and output. Furthermore, visual plausibility and clustering demonstrate that each component contributes differently to capturing the generative factors in topographic maps. Our proposed pipeline adds to the body of knowledge by delivering a CNN-VAE-based latent space interpretation model. This helps us learn the model’s decision and the importance of each component of latent space responsible for activating parts of the brain.
31
Zhang, Jian, Jin Yuan, Chuanzhen Li, and Bin Li. "An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning." Electronics 11, no. 12 (June 10, 2022): 1844. http://dx.doi.org/10.3390/electronics11121844.
Abstract:
A hybrid framework for solving the non-uniqueness problem in the inverse design of isomorphic metasurfaces is proposed. The framework consists of a representation learning (RL) module and a variational autoencoder-particle swarm optimization (VAE-PSO) algorithm module. The RL module is used to reduce the complex high-dimensional space into a low-dimensional space with obvious features, with the purpose of eliminating the many-to-one relationship between the original design space and response space. The VAE-PSO algorithm first encodes all meta-atoms into a continuous latent space through VAE and then applies PSO to search for an optimized latent vector whose corresponding metasurface fulfills the target response. This framework gives the solution paradigm of the ideal non-uniqueness situation, simplifies the complexity of the network, improves the running speed of the PSO algorithm, and obtains the global optimal solution with 94% accuracy on the test set.
32
Sha, Lei, and Thomas Lukasiewicz. "Text Attribute Control via Closed-Loop Disentanglement." Transactions of the Association for Computational Linguistics 12 (2024): 190–209. http://dx.doi.org/10.1162/tacl_a_00640.
Abstract:
Abstract Changing an attribute of a text without changing the content usually requires first disentangling the text into irrelevant attributes and content representations. After that, in the inference phase, the representation of one attribute is tuned to a different value, expecting that the corresponding attribute of the text can also be changed accordingly. The usual way of disentanglement is to add some constraints on the latent space of an encoder-decoder architecture, including adversarial-based constraints and mutual-information-based constraints. However, previous semi-supervised processes of attribute change are usually not enough to guarantee the success of attribute change and content preservation. In this paper, we propose a novel approach to achieve a robust control of attributes while enhancing content preservation. In this approach, we use a semi-supervised contrastive learning method to encourage the disentanglement of attributes in latent spaces. Differently from previous works, we re-disentangle the reconstructed sentence and compare the re-disentangled latent space with the original latent space, which makes a closed-loop disentanglement process. This also helps content preservation. In addition, the contrastive learning method is also able to replace the role of minimizing mutual information and adversarial training in the disentanglement process, which alleviates the computation cost. We conducted experiments on three text datasets, including the Yelp Service review dataset, the Amazon Product review dataset, and the GoEmotions dataset. The experimental results show the effectiveness of our model.
33
Khan, Shujaat. "Deep-Representation-Learning-Based Classification Strategy for Anticancer Peptides." Mathematics 12, no. 9 (April 27, 2024): 1330. http://dx.doi.org/10.3390/math12091330.
Abstract:
Cancer, with its complexity and numerous origins, continues to provide a huge challenge in medical research. Anticancer peptides are a potential treatment option, but identifying and synthesizing them on a large scale requires accurate prediction algorithms. This study presents an intuitive classification strategy, named ACP-LSE, based on representation learning, specifically, a deep latent-space encoding scheme. ACP-LSE can demonstrate notable advancements in classification outcomes, particularly in scenarios with limited sample sizes and abundant features. ACP-LSE differs from typical black-box approaches by focusing on representation learning. Utilizing an auto-encoder-inspired network, it embeds high-dimensional features, such as the composition of g-spaced amino acid pairs, into a compressed latent space. In contrast to conventional auto-encoders, ACP-LSE ensures that the learned feature set is both small and effective for classification, giving a transparent alternative. The suggested approach is tested on benchmark datasets and demonstrates higher performance compared to the current methods. The results indicate improved Matthew’s correlation coefficient and balanced accuracy, offering insights into crucial aspects for developing new ACPs. The implementation of the proposed ACP-LSE approach is accessible online, providing a valuable and reproducible resource for researchers in the field.
34
Bollon, Jordy, Michela Assale, Andrea Cina, Stefano Marangoni, Matteo Calabrese, Chiara Beatrice Salvemini, Jean Marc Christille, Stefano Gustincich, and Andrea Cavalli. "Investigating How Reproducibility and Geometrical Representation in UMAP Dimensionality Reduction Impact the Stratification of Breast Cancer Tumors." Applied Sciences 12, no. 9 (April 22, 2022): 4247. http://dx.doi.org/10.3390/app12094247.
Abstract:
Advances in next-generation sequencing have provided high-dimensional RNA-seq datasets, allowing the stratification of some tumor patients based on their transcriptomic profiles. Machine learning methods have been used to reduce and cluster high-dimensional data. Recently, uniform manifold approximation and projection (UMAP) was applied to project genomic datasets in low-dimensional Euclidean latent space. Here, we evaluated how different representations of the UMAP embedding can impact the analysis of breast cancer (BC) stratification. We projected BC RNA-seq data on Euclidean, spherical, and hyperbolic spaces, and stratified BC patients via clustering algorithms. We also proposed a pipeline to yield more reproducible clustering outputs. The results show how the selection of the latent space can affect downstream stratification results and suggest that the exploration of different geometrical representations is recommended to explore data structure and samples’ relationships.
35
Suo, Chuanzhe, Zhe Liu, Lingfei Mo, and Yunhui Liu. "LPD-AE: Latent Space Representation of Large-Scale 3D Point Cloud." IEEE Access 8 (2020): 108402–17. http://dx.doi.org/10.1109/access.2020.2999727.
36
You, Cong-Zhe, Zhen-Qiu Shu, and Hong-Hui Fan. "Non-negative sparse Laplacian regularized latent multi-view subspace clustering." Journal of Algorithms & Computational Technology 15 (January 2021): 174830262110249. http://dx.doi.org/10.1177/17483026211024904.
Abstract:
Recently, in the area of artificial intelligence and machine learning, subspace clustering of multi-view data is a research hotspot. The goal is to divide data samples from different sources into different groups. We proposed a new subspace clustering method for multi-view data which termed as Non-negative Sparse Laplacian regularized Latent Multi-view Subspace Clustering (NSL2MSC) in this paper. The method proposed in this paper learns the latent space representation of multi view data samples, and performs the data reconstruction on the latent space. The algorithm can cluster data in the latent representation space and use the relationship of different views. However, the traditional representation-based method does not consider the non-linear geometry inside the data, and may lose the local and similar information between the data in the learning process. By using the graph regularization method, we can not only capture the global low dimensional structural features of data, but also fully capture the nonlinear geometric structure information of data. The experimental results show that the proposed method is effective and its performance is better than most of the existing alternatives.
37
Bjerrum, Esben, and Boris Sattarov. "Improving Chemical Autoencoder Latent Space and Molecular De Novo Generation Diversity with Heteroencoders." Biomolecules 8, no. 4 (October 30, 2018): 131. http://dx.doi.org/10.3390/biom8040131.
Abstract:
Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead compound for employment early in a drug discovery project. Here, it is shown that the choice of chemical representation, such as strings from the simplified molecular-input line-entry system (SMILES), has a large influence on the properties of the latent space. It is further explored to what extent translating between different chemical representations influences the latent space similarity to the SMILES strings or circular fingerprints. By employing SMILES enumeration for either the encoder or decoder, it is found that the decoder has the largest influence on the properties of the latent space. Training a sequence to sequence heteroencoder based on recurrent neural networks (RNNs) with long short-term memory cells (LSTM) to predict different enumerated SMILES strings from the same canonical SMILES string gives the largest similarity between latent space distance and molecular similarity measured as circular fingerprints similarity. Using the output from the code layer in quantitative structure activity relationship (QSAR) of five molecular datasets shows that heteroencoder derived vectors markedly outperforms autoencoder derived vectors as well as models built using ECFP4 fingerprints, underlining the increased chemical relevance of the latent space. However, the use of enumeration during training of the decoder leads to a marked increase in the rate of decoding to different molecules than encoded, a tendency that can be counteracted with more complex network architectures.
38
Nguyễn, Tuấn, Nguyen Hai Hao, Dang Le Dinh Trang, Nguyen Van Tuan, and Cao Van Loi. "Robust anomaly detection methods for contamination network data." Journal of Military Science and Technology, no. 79 (May 19, 2022): 41–51. http://dx.doi.org/10.54939/1859-1043.j.mst.79.2022.41-51.
Abstract:
Recently, latent representation models, such as Shrink Autoencoder (SAE), have been demonstrated as robust feature representations for one-class learning-based network anomaly detection. In these studies, benchmark network datasets that are processed in laboratory environments to make them completely clean are often employed for constructing and evaluating such models. In real-world scenarios, however, we can not guarantee 100% to collect pure normal data for constructing latent representation models. Therefore, this work aims to investigate the characteristics of the latent representation of SAE in learning normal data under some contamination scenarios. This attempts to find out wherever the latent feature space of SAE is robust to contamination or not, and which contamination scenarios it prefers. We design a set of experiments using normal data contaminated with different anomaly types and different proportions of anomalies for the investigation. Other latent representation methods such as Denoising Autoencoder (DAE) and Principal component analysis (PCA) are also used for comparison with the performance of SAE. The experimental results on four CTU13 scenarios show that the latent representation of SAE often out-performs and are less sensitive to contamination than the others.
39
Hu, Dou, Lingwei Wei, Yaxin Liu, Wei Zhou, and Songlin Hu. "Structured Probabilistic Coding." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 11 (March 24, 2024): 12491–501. http://dx.doi.org/10.1609/aaai.v38i11.29142.
Abstract:
This paper presents a new supervised representation learning framework, namely structured probabilistic coding (SPC), to learn compact and informative representations from input related to the target task. SPC is an encoder-only probabilistic coding technology with a structured regularization from the target space. It can enhance the generalization ability of pre-trained language models for better language understanding. Specifically, our probabilistic coding simultaneously performs information encoding and task prediction in one module to more fully utilize the effective information from input data. It uses variational inference in the output space to reduce randomness and uncertainty. Besides, to better control the learning process of probabilistic representations, a structured regularization is proposed to promote uniformity across classes in the latent space. With the regularization term, SPC can preserve the Gaussian structure of the latent code and achieve better coverage of the hidden space with class uniformly. Experimental results on 12 natural language understanding tasks demonstrate that our SPC effectively improves the performance of pre-trained language models for classification and regression. Extensive experiments show that SPC can enhance the generalization capability, robustness to label noise, and clustering quality of output representations.
40
Koskinopoulou, Maria, Michail Maniadakis, and Panos Trahanias. "Speed Adaptation in Learning from Demonstration through Latent Space Formulation." Robotica 38, no. 10 (October 17, 2019): 1867–79. http://dx.doi.org/10.1017/s0263574719001449.
Abstract:
SUMMARYPerforming actions in a timely manner is an indispensable aspect in everyday human activities. Accordingly, it has to be present in robotic systems if they are going to seamlessly interact with humans. The current work addresses the problem of learning both the spatial and temporal characteristics of human motions from observation. We formulate learning as a mapping between two worlds (the observed and the action ones). This mapping is realized via an abstract intermediate representation termed “Latent Space.” Learned actions can be subsequently invoked in the context of more complex human–robot interaction (HRI) scenarios. Unlike previous learning from demonstration (LfD) methods that cope only with the spatial features of an action, the formulated scheme effectively encompasses spatial and temporal aspects. Learned actions are reproduced under the high-level control of a time-informed task planner. During the implementation of the studied scenarios, temporal and physical constraints may impose speed adaptations in the reproduced actions. The employed latent space representation readily supports such variations, giving rise to novel actions in the temporal domain. Experimental results demonstrate the effectiveness of the proposed scheme in the implementation of HRI scenarios. Finally, a set of well-defined evaluation metrics are introduced to assess the validity of the proposed approach considering the temporal and spatial consistency of the reproduced behaviors.
41
Cahani, Ilda, and Marcus Stiemer. "Mathematical optimization and machine learning to support PCB topology identification." Advances in Radio Science 21 (December 1, 2023): 25–35. http://dx.doi.org/10.5194/ars-21-25-2023.
Abstract:
Abstract. In this paper, we study an identification problem for schematics with different concurring topologies. A framework is proposed, that is both supported by mathematical optimization and machine learning algorithms. Through the use of Python libraries, such as scikit-rf, which allows for the emulation of network analyzer measurements, and a physical microstrip line simulation on PCBs, data for training and testing the framework are provided. In addition to an individual treatment of the concurring topologies and subsequent comparison, a method is introduced to tackle the identification of the optimum topology directly via a standard optimization or machine learning setup: An encoder-decoder sequence is trained with schematics of different topologies, to generate a flattened representation of the rated graph representation of the considered schematics. Still containing the relevant topology information in encoded (i.e., flattened) form, the so obtained latent space representations of schematics can be used for standard optimization of machine learning processes. Using now the encoder to map schematics on latent variables or the decoder to reconstruct schematics from their latent space representation, various machine learning and optimization setups can be applied to treat the given identification task. The proposed framework is presented and validated for a small model problem comprising different circuit topologies.
42
Tytarenko, Andrii. "Multi-step prediction in linearized latent state spaces for representation learning." System research and information technologies, no. 3 (October 30, 2022): 139–48. http://dx.doi.org/10.20535/srit.2308-8893.2022.3.09.
Abstract:
In this paper, we derive a novel method as a generalization over LCEs such as E2C. The method develops the idea of learning a locally linear state space by adding a multi-step prediction, thus allowing for more explicit control over the curvature. We show that the method outperforms E2C without drastic model changes which come with other works, such as PCC and P3C. We discuss the relation between E2C and the presented method and derive update equations. We provide empirical evidence, which suggests that by considering the multi-step prediction, our method – ms-E2C – allows learning much better latent state spaces in terms of curvature and next state predictability. Finally, we also discuss certain stability challenges we encounter with multi-step predictions and how to mitigate them.
43
Liao, Chenxi, Masataka Sawayama, and Bei Xiao. "Unsupervised learning reveals interpretable latent representations for translucency perception." PLOS Computational Biology 19, no. 2 (February 8, 2023): e1010878. http://dx.doi.org/10.1371/journal.pcbi.1010878.
Abstract:
Humans constantly assess the appearance of materials to plan actions, such as stepping on icy roads without slipping. Visual inference of materials is important but challenging because a given material can appear dramatically different in various scenes. This problem especially stands out for translucent materials, whose appearance strongly depends on lighting, geometry, and viewpoint. Despite this, humans can still distinguish between different materials, and it remains unsolved how to systematically discover visual features pertinent to material inference from natural images. Here, we develop an unsupervised style-based image generation model to identify perceptually relevant dimensions for translucent material appearances from photographs. We find our model, with its layer-wise latent representation, can synthesize images of diverse and realistic materials. Importantly, without supervision, human-understandable scene attributes, including the object’s shape, material, and body color, spontaneously emerge in the model’s layer-wise latent space in a scale-specific manner. By embedding an image into the learned latent space, we can manipulate specific layers’ latent code to modify the appearance of the object in the image. Specifically, we find that manipulation on the early-layers (coarse spatial scale) transforms the object’s shape, while manipulation on the later-layers (fine spatial scale) modifies its body color. The middle-layers of the latent space selectively encode translucency features and manipulation of such layers coherently modifies the translucency appearance, without changing the object’s shape or body color. Moreover, we find the middle-layers of the latent space can successfully predict human translucency ratings, suggesting that translucent impressions are established in mid-to-low spatial scale features. This layer-wise latent representation allows us to systematically discover perceptually relevant image features for human translucency perception. Together, our findings reveal that learning the scale-specific statistical structure of natural images might be crucial for humans to efficiently represent material properties across contexts.
44
Xie, Haoyu, Changqi Wang, Mingkai Zheng, Minjing Dong, Shan You, Chong Fu, and Chang Xu. "Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 2938–46. http://dx.doi.org/10.1609/aaai.v37i3.25396.
Abstract:
Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space. However, there exist inaccurate pseudo-labels which map the ambiguous representations of pixels to the wrong classes due to the limited cognitive ability of the model. In this paper, we define pixel-wise representations from a new perspective of probability theory and propose a Probabilistic Representation Contrastive Learning (PRCL) framework that improves representation quality by taking its probability into consideration. Through modelling the mapping from pixels to representations as the probability via multivariate Gaussian distributions, we can tune the contribution of the ambiguous representations to tolerate the risk of inaccurate pseudo-labels. Furthermore, we define prototypes in the form of distributions, which indicates the confidence of a class, while the point prototype cannot. More- over, we propose to regularize the distribution variance to enhance the reliability of representations. Taking advantage of these benefits, high-quality feature representations can be derived in the latent space, thereby the performance of se- mantic segmentation can be further improved. We conduct sufficient experiment to evaluate PRCL on Pascal VOC and CityScapes to demonstrate its superiority. The code is available at https://github.com/Haoyu-Xie/PRCL.
45
Cristovao, Paulino, Hidemoto Nakada, Yusuke Tanimura, and Hideki Asoh. "Generating In-Between Images Through Learned Latent Space Representation Using Variational Autoencoders." IEEE Access 8 (2020): 149456–67. http://dx.doi.org/10.1109/access.2020.3016313.
46
Jang, Gye-Bong, and Sung-Bae Cho. "Feature Space Transformation for Fault Diagnosis of Rotating Machinery under Different Working Conditions." Sensors 21, no. 4 (February 18, 2021): 1417. http://dx.doi.org/10.3390/s21041417.
Abstract:
In recent years, various deep learning models have been developed for the fault diagnosis of rotating machines. However, in practical applications related to fault diagnosis, it is difficult to immediately implement a trained model because the distribution of source data and target domain data have different distributions. Additionally, collecting failure data for various operating conditions is time consuming and expensive. In this paper, we introduce a new transformation method for the latent space between domains using the source domain and normal data of the target domain that can be easily collected. Inspired by semantic transformations in an embedded space in the field of word embedding, discrepancies between the distribution of the source and target domains are minimized by transforming the latent representation space in which fault attributes are preserved. To match the feature area and distribution, spatial attention is applied to learn the latent feature spaces, and the 1D CNN LSTM architecture is implemented to maximize the intra-class classification. The proposed model was validated for two types of rotating machines such as a dataset of rolling bearings as CWRU and a gearbox dataset of heavy machinery. Experimental results show the proposed method has higher cross-domain diagnostic accuracy than others, therefore showing reliable generalization performance in rotating machines operating under various conditions.
47
Kumaran, Vikram, Bradford Mott, and James Lester. "Generating Game Levels for Multiple Distinct Games with a Common Latent Space." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 15, no. 1 (October 1, 2020): 102–8. http://dx.doi.org/10.1609/aiide.v15i1.7418.
Abstract:
Generative adversarial networks (GANs) are showing significant promise for procedural content generation (PCG) of game levels. GAN models generate game levels by mapping a low dimensional latent space to game levels in the game space. An intriguing challenge in GAN-based PCG is enabling GANs to produce game levels for multiple distinct games with similar gameplay characteristics using a common underlying low-dimensional representation. In this paper, we present a method for training a novel GAN-based PCG architecture that generates levels in multiple distinct games, starting from a common gameplay action sequence. We evaluate the solvability of the generated games using an automated playing agent and show how the generated game levels are separate representations of the same gameplay by quantifying the similarity between the solution action sequences for the game levels. By probing the common latent space, we show how our approach provides control over the levels generated in distinct games for the presence of desired gameplay patterns in the generated game levels. Results also demonstrate that the GAN-based PCG approach creates novel game levels in multiple distinct games, as indicated by the distance between the action sequences required to solve the game levels.
48
Kumaran, Vikram, Bradford Mott, and James Lester. "Generating Game Levels for Multiple Distinct Games with a Common Latent Space." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 16, no. 1 (October 1, 2020): 109–15. http://dx.doi.org/10.1609/aiide.v16i1.7485.
Abstract:
Generative adversarial networks (GANs) are showing significant promise for procedural content generation (PCG) of game levels. GAN models generate game levels by mapping a low dimensional latent space to game levels in the game space. An intriguing challenge in GAN-based PCG is enabling GANs to produce game levels for multiple distinct games with similar gameplay characteristics using a common underlying low-dimensional representation. In this paper, we present a method for training a novel GAN-based PCG architecture that generates levels in multiple distinct games, starting from a common gameplay action sequence. We evaluate the solvability of the generated games using an automated playing agent and show how the generated game levels are separate representations of the same gameplay by quantifying the similarity between the solution action sequences for the game levels. By probing the common latent space, we show how our approach provides control over the levels generated in distinct games for the presence of desired gameplay patterns in the generated game levels. Results also demonstrate that the GAN-based PCG approach creates novel game levels in multiple distinct games, as indicated by the distance between the action sequences required to solve the game levels.
49
Chen, Zhuo, Haimei Zhao, Chaoyue Wang, Bo Yuan, and Xiu Li. "Dual Mapping of 2D StyleGAN for 3D-Aware Image Generation and Manipulation (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 21 (March 24, 2024): 23458–59. http://dx.doi.org/10.1609/aaai.v38i21.30428.
Abstract:
3D-aware GANs successfully solve the problem of 3D-consistency generation and furthermore provide a 3D shape of the generated object. However, the application of the volume renderer disturbs the disentanglement of the latent space, which makes it difficult to manipulate 3D-aware GANs and lowers the image quality of style-based generators. In this work, we devise a dual-mapping framework to make the generated images of pretrained 2D StyleGAN consistent in 3D space. We utilize a tri-plane representation to estimate the 3D shape of the generated object and two mapping networks to bridge the latent space of StyleGAN and the 3D tri-plane space. Our method does not alter the parameters of the pretrained generator, which means the interpretability of latent space is preserved for various image manipulations. Experiments show that our method lifts the 3D awareness of pretrained 2D StyleGAN to 3D-aware GANs and outperforms the 3D-aware GANs in controllability and image quality.
50
Hajihassani, Omid, Omid Ardakanian, and Hamzeh Khazaei. "Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach." ACM Transactions on Internet of Things 3, no. 1 (February 28, 2022): 1–26. http://dx.doi.org/10.1145/3485820.
Abstract:
The abundance of data collected by sensors in Internet of Things devices and the success of deep neural networks in uncovering hidden patterns in time series data have led to mounting privacy concerns. This is because private and sensitive information can be potentially learned from sensor data by applications that have access to this data. In this article, we aim to examine the tradeoff between utility and privacy loss by learning low-dimensional representations that are useful for data obfuscation. We propose deterministic and probabilistic transformations in the latent space of a variational autoencoder to synthesize time series data such that intrusive inferences are prevented while desired inferences can still be made with sufficient accuracy. In the deterministic case, we use a linear transformation to move the representation of input data in the latent space such that the reconstructed data is likely to have the same public attribute but a different private attribute than the original input data. In the probabilistic case, we apply the linear transformation to the latent representation of input data with some probability. We compare our technique with autoencoder-based anonymization techniques and additionally show that it can anonymize data in real time on resource-constrained edge devices.