mlsanityData to 7 Oct 2026

Disentangling by Factorising

arXiv 1802.05983 ↗First posted 16 Feb 2018stat.ML cs.LGcited by 614

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon β-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

Key facts. Cited by 614 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 133; 2022: 129; 2023: 105; 2024: 97; 2025: 87; 2026: 63.

614 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
  3. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  4. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probingcited by 328
  5. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  6. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  7. 2021Towards Causal Representation Learningcited by 207
  8. 2021The Values Encoded in Machine Learning Researchcited by 172
  9. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  10. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  11. 2024Improving Dictionary Learning with Gated Sparse Autoencoderscited by 171
  12. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 154
38 more
  1. 2021Illiterate DALL-E Learns to Composecited by 147
  2. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  3. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  4. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
  5. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  6. 2022Disentangled Representation Learningcited by 111
  7. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  8. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 96
  9. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  10. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  11. 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Taskcited by 91
  12. 2023Object-Centric Slot Diffusioncited by 90
  13. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  14. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  15. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  16. 2021BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Datacited by 75
  17. 2025A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelscited by 73
  18. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  19. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  20. 2023No Representation Rules Them All in Category Discoverycited by 61
  21. 2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 60
  22. 2022Factorizing Knowledge in Neural Networkscited by 59
  23. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  24. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  25. 2022Diversify and Disambiguate: Learning From Underspecified Datacited by 55
  26. 2022Function Classes for Identifiable Nonlinear Independent Component Analysiscited by 53
  27. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  28. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  29. 2023Score-based Causal Representation Learning with Interventionscited by 49
  30. 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
  31. 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
  32. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  33. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  34. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  35. 2022Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learningcited by 44
  36. 2022Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Languagecited by 42
  37. 2023Disentanglement via Latent Quantizationcited by 40
  38. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37

50 most cited of 614 All 614 (JSON)