mlsanityData to 7 Oct 2026

Understanding disentangling in β-VAE

arXiv 1804.03599 ↗First posted 10 Apr 2018stat.ML cs.AI cs.LGcited by 332

Not on the map. Why?

Abstract (arXiv)

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising the modified ELBO bound in β-VAE, as training progresses. From these insights, we propose a modification to the training regime of β-VAE, that progressively increases the information capacity of the latent code during training. This modification facilitates the robust learning of disentangled representations in β-VAE, without the previous trade-off in reconstruction accuracy.

Key facts. Cited by 332 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 2; 2020: 1; 2021: 62; 2022: 86; 2023: 61; 2024: 35; 2025: 38; 2026: 47.

332 papers.

Sort:

By area:

  1. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
  2. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  3. 2019Causal Confusion in Imitation Learningcited by 286
  4. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  5. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  6. 2022Disentangled Representation Learningcited by 111
  7. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  8. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  9. 2022Tutorial on amortized optimizationcited by 83
  10. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  11. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  12. 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 76
38 more
  1. 2022On scientific understanding with artificial intelligencecited by 68
  2. 2022Challenges and Opportunities in Offline Reinforcement Learning from Visual Observationscited by 63
  3. 2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 60
  4. 2022Factorizing Knowledge in Neural Networkscited by 59
  5. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  6. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  7. 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
  8. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  9. 2021Disentangling Hate in Online Memescited by 46
  10. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  11. 2023Provably Learning Object-Centric Representationscited by 45
  12. 2021Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flowscited by 44
  13. 2022Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Languagecited by 42
  14. 2023Provable Compositional Generalization for Object-Centric Learningcited by 41
  15. 2023Neither hype nor gloom do DNNs justicecited by 40
  16. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  17. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
  18. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  19. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  20. 2023FIND: A Function Description Benchmark for Evaluating Interpretability Methodscited by 32
  21. 2021PAC-Bayes Information Bottleneckcited by 28
  22. 2022Embrace the Gap: VAEs Perform Independent Mechanism Analysiscited by 28
  23. 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learningcited by 27
  24. 2021Learning to Learn Graph Topologiescited by 26
  25. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  26. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  27. 2021Physics Informed Neural Networks for Control Oriented Thermal Modeling of Buildingscited by 24
  28. 2022Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddingscited by 22
  29. 2023Variational Autoencoding Neural Operatorscited by 22
  30. 2021Creativity and Machine Learning: A Surveycited by 21
  31. 2023Fast Diffusion Modelcited by 20
  32. 2021Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoderscited by 19
  33. 2022Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learningcited by 19
  34. 2022Improving aircraft performance using machine learning: a reviewcited by 19
  35. 2024An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Predictioncited by 19
  36. 2021Deep Deterministic Information Bottleneck with Matrix-based Entropy Functionalcited by 18
  37. 2021Lifelong Teacher-Student Network Learningcited by 18
  38. 2021Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activitycited by 18

50 most cited of 332 All 332 (JSON)