mlsanityData to 7 Oct 2026

Linear Causal Disentanglement via Interventions

arXiv 2211.16467 ↗First posted 29 Nov 2022stat.ML cs.LGcited by 84

Not on the map. Why?

Abstract (arXiv)

Causal disentanglement seeks a representation of data involving latent variables that relate to one another via a causal model. A representation is identifiable if both the latent model and the transformation from latent to observed variables are unique. In this paper, we study observed variables that are a linear transformation of a linear latent causal model. Data from interventions are necessary for identifiability: if one latent variable is missing an intervention, we show that there exist distinct models that cannot be distinguished. Conversely, we show that a single intervention on each latent variable is sufficient for identifiability. Our proof uses a generalization of the RQ decomposition of a matrix that replaces the usual orthogonal and upper triangular conditions with analogues depending on a partial order on the rows of the matrix, with partial order determined by a latent causal model. We corroborate our theoretical results with a method for causal disentanglement that accurately recovers a latent causal model.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Builds on 16 of its 51 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

16 of 51 references.

References · 16

  1. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  2. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  3. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  4. 2022Weakly supervised causal representation learningcited by 140
  5. 2022Interventional Causal Representation Learningcited by 140
  6. 2018Characterizing and Learning Equivalence Classes of Causal DAGs under Interventionscited by 76
  7. 2019Permutation-Based Causal Structure Learning with Unknown Intervention Targetscited by 69
  8. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  9. 2021Learning latent causal graphs via mixture oraclescited by 55
  10. 2021Identifiable Deep Generative Models via Sparse Decodingcited by 54
  11. 2022Causal Structure Learning: a Combinatorial Perspectivecited by 46
  12. 2021Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learningcited by 30
4 more
  1. 2022Causal Structure Discovery between Clusters of Nodes Induced by Latent Factorscited by 18
  2. 2019Anchored Causal Inference in the Presence of Measurement Errorcited by 11
  3. 2021Scalable Intervention Target Estimation in Linear Modelscited by 10
  4. 2015Anchored Discrete Factor Analysiscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 25; 2024: 20; 2025: 16; 2026: 23.

84 papers.

Sort:

By area:

  1. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  2. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  3. 2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
  4. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 72
  5. 2024Causal Representation Learning from Multiple Distributions: A General Settingcited by 67
  6. 2023Causal Component Analysiscited by 56
  7. 2023Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolationcited by 56
  8. 2023Score-based Causal Representation Learning with Interventionscited by 49
  9. 2023Learning nonparametric latent causal graphs with unknown interventionscited by 34
  10. 2023General Identifiability and Achievability for Causal Representation Learningcited by 34
  11. 2024A Sparsity Principle for Partially Observable Causal Representation Learningcited by 34
  12. 2023Unpaired Multi-Domain Causal Representation Learningcited by 32
38 more
  1. 2023Leveraging sparse and shared feature activations for disentangled representation learningcited by 32
  2. 2023Causal Representation Learning Made Identifiable by Grouping of Observational Variablescited by 30
  3. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 30
  4. 2024Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Modelscited by 29
  5. 2023Multi-Domain Causal Representation Learning via Weak Distributional Invariancescited by 23
  6. 2023Identifiable Latent Polynomial Causal Models Through the Lens of Changecited by 23
  7. 2024Marrying Causal Representation Learning with Dynamical Systems for Sciencecited by 22
  8. 2023Identifying Representations for Intervention Extrapolationcited by 21
  9. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  10. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  11. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  12. 2023Self-Supervised Disentanglement by Leveraging Structure in Data Augmentationscited by 16
  13. 2024Analyzing (In)Abilities of SAEs via Formal Languagescited by 16
  14. 2023Targeted Reduction of Causal Modelscited by 15
  15. 2024Linear Causal Representation Learning from Unknown Multi-node Interventionscited by 14
  16. 2025I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?cited by 13
  17. 2024Smoke and Mirrors in Causal Downstream Taskscited by 12
  18. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  19. 2025Towards Interpretable Deep Generative Models via Causal Representation Learningcited by 12
  20. 2024Beyond DAGs: A Latent Partial Causal Model for Multimodal Learningcited by 9
  21. 2024Automated Discovery of Pairwise Interactions from Unstructured Datacited by 8
  22. 2024Language Agents Meet Causality -- Bridging LLMs and Causal World Modelscited by 8
  23. 2024Identifiability Guarantees for Causal Disentanglement from Purely Observational Datacited by 7
  24. 2025Robustness of Nonlinear Representation Learningcited by 7
  25. 2024Propensity Score Alignment of Unpaired Multimodal Datacited by 6
  26. 2025Debiasing Reward Models by Representation Learning with Guaranteescited by 6
  27. 2023Invariance & Causal Representation Learning: Prospects and Limitationscited by 5
  28. 2024Towards Identifiable Latent Additive Noise Modelscited by 5
  29. 2024Identifiability Analysis of Linear ODE Systems with Hidden Confounderscited by 5
  30. 2025Sanity Checking Causal Representation Learning on a Simple Real-World Systemcited by 5
  31. 2023Learning Causal Graphs via Monotone Triangular Transport Mapscited by 4
  32. 2023Neuro-Causal Factor Analysiscited by 4
  33. 2023Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Modelscited by 4
  34. 2024Identifying General Mechanism Shifts in Linear Causal Representationscited by 4
  35. 2025The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representationscited by 4
  36. 2026Structural Causal Bottleneck Modelscited by 4
  37. 2026Causal Representation Learning from General Environments under Nonparametric Mixingcited by 4
  38. 2024Learning Invariant Causal Mechanism from Vision-Language Modelscited by 3

50 most cited of 84 All 84 (JSON)