mlsanityData to 14 Oct 2026

Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness

arXiv 1811.00007 ↗First posted 31 Oct 2018stat.ML cs.LGcited by 108

Not on the map. Why?

Abstract (arXiv)

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards this goal have been proposed in recent times, a commonly accepted definition and validation procedure is missing. We provide a causal perspective on representation learning which covers disentanglement and domain shift robustness as special cases. Our causal framework allows us to introduce a new metric for the quantitative evaluation of deep latent variable models. We show how this metric can be estimated from labeled observational data and further provide an efficient estimation algorithm that scales linearly in the dataset size.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 26; 2022: 18; 2023: 31; 2024: 9; 2025: 14; 2026: 10.

108 papers.

Sort:

By area:

  1. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  2. 2021Towards Causal Representation Learningcited by 209
  3. 2022Disentangled Representation Learningcited by 112
  4. 2021Counterfactual Generative Networkscited by 111
  5. 2021Causal Attention for Vision-Language Taskscited by 111
  6. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  7. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  8. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  9. 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcutscited by 63
  10. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  11. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  12. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
38 more
  1. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  2. 2022Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Languagecited by 42
  3. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  4. 2022From Statistical to Causal Learningcited by 40
  5. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  6. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  7. 2023Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignmentcited by 32
  8. 2022Invariant Causal Mechanisms through Distribution Matchingcited by 31
  9. 2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
  10. 2023Group Robust Classification Without Any Group Informationcited by 25
  11. 2022DCI-ES: An Extended Disentanglement Framework with Connections to Identifiabilitycited by 23
  12. 2021Towards Building A Group-based Unsupervised Representation Disentanglement Frameworkcited by 22
  13. 2021On Causally Disentangled Representationscited by 22
  14. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  15. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 22
  16. 2023Self-Supervised Disentanglement by Leveraging Structure in Data Augmentationscited by 17
  17. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 16
  18. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  19. 2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
  20. 2023Generative Causal Representation Learning for Out-of-Distribution Motion Forecastingcited by 13
  21. 2021Bayesian multiscale deep generative model for the solution of high-dimensional inverse problemscited by 12
  22. 2023Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalizationcited by 12
  23. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  24. 2021Intact-VAE: Estimating Treatment Effects under Unobserved Confoundingcited by 10
  25. 2021Object-Centric Representation Learning with Generative Spatial-Temporal Factorizationcited by 10
  26. 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
  27. 2022Deconfounding to Explanation Evaluation in Graph Neural Networkscited by 10
  28. 2021Disentanglement and Generalization Under Correlation Shiftscited by 8
  29. 2023Moderately Distributional Exploration for Domain Generalizationcited by 8
  30. 2023Hacking Task Confounder in Meta-Learningcited by 8
  31. 2025There Was Never a Bottleneck in Concept Bottleneck Modelscited by 8
  32. 2021Sill-Net: Feature Augmentation with Separated Illumination Representationcited by 7
  33. 2023Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitationscited by 7
  34. 2023C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confoundercited by 7
  35. 2025From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?cited by 7
  36. 2022Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalizationcited by 6
  37. 2023Deep Kernel Principal Component Analysis for Multi-level Feature Learningcited by 6
  38. 2021Demystifying Inductive Biases for β-VAE Based Architecturescited by 5

50 most cited of 108 All 108 (JSON)