mlsanityData to 14 Oct 2026

Learning Independent Causal Mechanisms

arXiv 1712.00961 ↗First posted 4 Dec 2017cs.LG stat.MLcited by 105

Not on the map. Why?

Abstract (arXiv)

Statistical learning relies upon data sampled from a distribution, and we usually do not care what actually generated it in the first place. From the point of view of causal modeling, the structure of each distribution is induced by physical mechanisms that give rise to dependences between observables. Mechanisms, however, can be meaningful autonomous modules of generative models that make sense beyond a particular entailed data distribution, lending themselves to transfer between problems. We develop an algorithm to recover a set of independent (inverse) mechanisms from a set of transformed data points. The approach is unsupervised and based on a set of experts that compete for data generated by the mechanisms, driving specialization. We analyze the proposed method in a series of experiments on image data. Each expert learns to map a subset of the transformed data back to a reference distribution. The learned mechanisms generalize to novel domains. We discuss implications for transfer learning and links to recent trends in generative modeling.

Key facts. Cited by 105 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 32; 2022: 24; 2023: 20; 2024: 10; 2025: 9; 2026: 9.

105 papers.

Sort:

By area:

  1. 2021Towards Causal Representation Learningcited by 209
  2. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  3. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  4. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 138
  5. 2021Independent mechanism analysis, a new concept?cited by 97
  6. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  7. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  8. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 84
  9. 2023Modular Deep Learningcited by 83
  10. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  11. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Historiescited by 71
  12. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 71
38 more
  1. 2021Continual Learning via Local Module Compositioncited by 63
  2. 2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 61
  3. 2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
  4. 2021Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progressioncited by 48
  5. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  6. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  7. 2022A Causal Lens for Controllable Text Generationcited by 45
  8. 2022Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Datacited by 42
  9. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  10. 2022From Statistical to Causal Learningcited by 40
  11. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  12. 2023Measuring axiomatic soundness of counterfactual image modelscited by 34
  13. 2023Leveraging sparse and shared feature activations for disentangled representation learningcited by 32
  14. 2022Factored Adaptation for Non-Stationary Reinforcement Learningcited by 30
  15. 2021Unsupervised Object Learning via Common Fatecited by 29
  16. 2022Combining Modular Skills in Multitask Learningcited by 28
  17. 2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
  18. 2025A Closer Look at Multimodal Representation Collapsecited by 28
  19. 2021Dynamic Inference with Neural Interpreterscited by 24
  20. 2021Learning Domain Invariant Representations for Generalizable Person Re-Identificationcited by 22
  21. 2023Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learningcited by 22
  22. 2023Invariant Learning via Probability of Sufficient and Necessary Causescited by 22
  23. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 22
  24. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20
  25. 2021Transformers with Competitive Ensembles of Independent Mechanismscited by 19
  26. 2022Discrete Key-Value Bottleneckcited by 18
  27. 2021Object-Aware Regularization for Addressing Causal Confusion in Imitation Learningcited by 17
  28. 2021Deconfounded Visual Groundingcited by 16
  29. 2021Improving Weakly-supervised Object Localization via Causal Interventioncited by 14
  30. 2022Equivariance and Invariance Inductive Bias for Learning from Insufficient Datacited by 14
  31. 2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
  32. 2021Empowering Language Understanding with Counterfactual Reasoningcited by 13
  33. 2024Compositional Risk Minimizationcited by 13
  34. 2021Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglementcited by 12
  35. 2021Towards Unbiased Visual Emotion Recognition via Causal Interventioncited by 11
  36. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  37. 2021Quantifying Local Specialization in Deep Neural Networkscited by 10
  38. 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learningcited by 10

50 most cited of 105 All 105 (JSON)