mlsanityData to 7 Oct 2026

Invariance & Causal Representation Learning: Prospects and Limitations

arXiv 2312.03580 ↗First posted 6 Dec 2023stat.ML cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

In causal models, a given mechanism is assumed to be invariant to changes of other mechanisms. While this principle has been utilized for inference in settings where the causal variables are observed, theoretical insights when the variables of interest are latent are largely missing. We assay the connection between invariance and causal representation learning by establishing impossibility results which show that invariance alone is insufficient to identify latent causal variables. Together with practical considerations, we use these theoretical findings to highlight the need for additional constraints in order to identify representations by exploiting invariance.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 56 references that are in the map. First posted on arXiv 6 Dec 2023.

Builds on

36 of 56 references.

References · 36

  1. 2019Invariant Risk Minimizationcited by 1,832
  2. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  3. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  4. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  5. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  6. 2020The Risks of Invariant Risk Minimizationcited by 262
  7. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  8. 2022Weakly supervised causal representation learningcited by 140
  9. 2022Interventional Causal Representation Learningcited by 140
  10. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  11. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 125
  12. 2018Invariance, Causality and Robustnesscited by 123
24 more
  1. 2018Anchor regression: heterogeneous data meets causalitycited by 116
  2. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  3. 2020On Linear Identifiability of Learned Representationscited by 103
  4. 2021Independent mechanism analysis, a new concept?cited by 96
  5. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 96
  6. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  7. 2022Linear Causal Disentanglement via Interventionscited by 84
  8. 2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
  9. 2020Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Seriescited by 76
  10. 2020Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effectscited by 72
  11. 2020A causal framework for distribution generalizationcited by 68
  12. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  13. 2022Temporally Disentangled Representation Learningcited by 59
  14. 2022Function Classes for Identifiable Nonlinear Independent Component Analysiscited by 53
  15. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 50
  16. 2023Score-based Causal Representation Learning with Interventionscited by 49
  17. 2022Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learningcited by 44
  18. 2023BISCUIT: Causal Representation Learning from Binary Interactionscited by 38
  19. 2022Identifying Weight-Variant Latent Causal Modelscited by 33
  20. 2022Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modelingcited by 33
  21. 2023Identifiable Latent Polynomial Causal Models Through the Lens of Changecited by 23
  22. 2023Identifying Representations for Intervention Extrapolationcited by 21
  23. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  24. 2018Learning stable and predictive structures in kinetic systems: Benefits of a causal approachcited by 12

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  2. 2025What is causal about causal models and representations?cited by 6
  3. 2024Towards Identifiable Latent Additive Noise Modelscited by 5
  4. 2024Linear causal disentanglement via higher-order cumulantscited by 1
  5. 2025Structured Contrastive Learning for Interpretable Latent Representationscited by 0