mlsanityData to 14 Oct 2026

Variational Inference of Disentangled Latent Concepts from Unlabeled Observations

arXiv 1711.00848 ↗First posted 2 Nov 2017cs.LG cs.AI cs.CVcited by 241

Not on the map. Why?

Abstract (arXiv)

Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks, interpretability, etc. We consider the problem of unsupervised learning of disentangled representations from large pool of unlabeled observations, and propose a variational inference based approach to infer disentangled latent factors. We introduce a regularizer on the expectation of the approximate posterior over observed data that encourages the disentanglement. We also propose a new disentanglement metric which is better aligned with the qualitative disentanglement observed in the decoder's output. We empirically observe significant improvement over existing methods in terms of both disentanglement and data likelihood (reconstruction quality).

Key facts. Cited by 241 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 54; 2022: 51; 2023: 46; 2024: 37; 2025: 30; 2026: 23.

241 papers.

Sort:

By area:

  1. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  2. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 211
  3. 2021Illiterate DALL-E Learns to Composecited by 147
  4. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 133
  5. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 129
  6. 2022Disentangled Representation Learningcited by 112
  7. 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Taskcited by 93
  8. 2023Object-Centric Slot Diffusioncited by 90
  9. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  10. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 77
  11. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  12. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
38 more
  1. 2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 61
  2. 2022Factorizing Knowledge in Neural Networkscited by 59
  3. 2022Function Classes for Identifiable Nonlinear Independent Component Analysiscited by 53
  4. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 51
  5. 2023Score-based Causal Representation Learning with Interventionscited by 49
  6. 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
  7. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  8. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  9. 2022Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learningcited by 44
  10. 2022Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Languagecited by 42
  11. 2023Disentanglement via Latent Quantizationcited by 40
  12. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  13. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  14. 2022Neural Systematic Bindercited by 37
  15. 2023Subspace Identification for Multi-Source Domain Adaptationcited by 37
  16. 2021Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generationcited by 35
  17. 2024Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Spacecited by 35
  18. 2021Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning Viewcited by 34
  19. 2023Measuring axiomatic soundness of counterfactual image modelscited by 34
  20. 2023Generalizing Nonlinear ICA Beyond Structural Sparsitycited by 34
  21. 2022StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesiscited by 33
  22. 2021An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wildcited by 30
  23. 2022Disentanglement with Biological Constraints: A Theory of Functional Cell Typescited by 30
  24. 2023Towards Robust Metrics for Concept Representation Evaluationcited by 29
  25. 2022Embrace the Gap: VAEs Perform Independent Mechanism Analysiscited by 28
  26. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  27. 2021Commutative Lie Group VAE for Disentanglement Learningcited by 27
  28. 2024Diffusion Model with Cross Attention as an Inductive Bias for Disentanglementcited by 27
  29. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  30. 2023Multifactor Sequential Disentanglement via Structured Koopman Autoencoderscited by 24
  31. 2023Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Designcited by 23
  32. 2021Towards Building A Group-based Unsupervised Representation Disentanglement Frameworkcited by 22
  33. 2021On Causally Disentangled Representationscited by 22
  34. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  35. 2021Learning disentangled representations via product manifold projectioncited by 20
  36. 2021Exploring Autoencoder-based Error-bounded Compression for Scientific Datacited by 19
  37. 2022Decoupling Local and Global Representations of Time Seriescited by 17
  38. 2022Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoderscited by 17

50 most cited of 241 All 241 (JSON)