mlsanityData to 7 Oct 2026

On Causally Disentangled Representations

arXiv 2112.05746 ↗First posted 10 Dec 2021cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence assumptions, more recently, weak supervision and correlated features have been explored, but without a causal view of the generative process. In contrast, we work under the regime of a causal generative process where generative factors are either independent or can be potentially confounded by a set of observed or unobserved confounders. We present an analysis of disentangled representations through the notion of disentangled causal process. We motivate the need for new metrics and datasets to study causal disentanglement and propose two evaluation metrics and a dataset. We show that our metrics capture the desiderata of disentangled causal process. Finally, we perform an empirical study on state of the art disentangled representation learners using our metrics and dataset to evaluate them from causal perspective.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

28 of 45 references.

References · 28

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  3. 2016The Mythos of Model Interpretabilitycited by 716
  4. 2018Disentangling by Factorisingcited by 614
  5. 2019Counterfactual Visual Explanationscited by 312
  6. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  7. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  8. 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200
  9. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  10. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  11. 2019Causal Discovery with Reinforcement Learningcited by 145
  12. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
16 more
  1. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  2. 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
  3. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  4. 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
  5. 2019On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Datasetcited by 100
  6. 2020On Disentangled Representations Learned From Correlated Datacited by 94
  7. 2020Counterfactual Data Augmentation using Locally Factored Dynamicscited by 93
  8. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  9. 2019Neural Network Attributions: A Causal Perspectivecited by 77
  10. 2020S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generationcited by 63
  11. 2020On the Transfer of Disentangled Representations in Realistic Settingscited by 63
  12. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 47
  13. 2020Semi-Supervised StyleGAN for Disentanglement Learningcited by 43
  14. 2020Generative causal explanations of black-box classifierscited by 41
  15. 2019Weakly Supervised Disentanglement by Pairwise Similaritiescited by 22
  16. 2019Causal Regularizationcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 5; 2025: 3; 2026: 2.

22 papers.

Sort:

  1. 2022Disentangled Representation Learningcited by 111
  2. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  3. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  4. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  5. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  6. 2023Emerging Synergies in Causality and Deep Generative Models: A Surveycited by 10
  7. 2023C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confoundercited by 7
  8. 2022Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testingcited by 6
  9. 2025When Shift Happens - Confounding Is to Blamecited by 5
  10. 2023Entity Aware Modelling: A Surveycited by 4
  11. 2022Counterfactual Generation Under Confoundingcited by 2
  12. 2023Causally Disentangled Generative Variational AutoEncodercited by 2
10 more
  1. 2024Analyzing Generative Models by Manifold Entropic Metricscited by 2
  2. 2023On Counterfactual Data Augmentation Under Confoundingcited by 1
  3. 2024Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagerycited by 1
  4. 2024Measuring Orthogonality in Representations of Generative Modelscited by 1
  5. 2024Improved Monte Carlo Planning via Causal Disentanglement for Structurally-Decomposed Markov Decision Processescited by 0
  6. 2024Independence Constrained Disentangled Representation Learning from Epistemological Perspectivecited by 0
  7. 2025Causal Disentanglement Learning for Accurate Anomaly Detection in Multivariate Time Seriescited by 0
  8. 2025Towards Unsupervised Causal Representation Learning via Latent Additive Noise Model Causal Autoencoderscited by 0
  9. 2026Disentanglement-Based Equivariant Learning for Compositional VQAcited by 0
  10. 2026Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Modelscited by 0