mlsanityData to 14 Oct 2026

Multi-Domain Causal Representation Learning via Weak Distributional Invariances

arXiv 2310.02854 ↗First posted 4 Oct 2023cs.LG stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

Causal representation learning has emerged as the center of action in causal machine learning research. In particular, multi-domain datasets present a natural opportunity for showcasing the advantages of causal representation learning over standard unsupervised representation learning. While recent works have taken crucial steps towards learning causal representations, they often lack applicability to multi-domain datasets due to over-simplifying assumptions about the data; e.g. each domain comes from a different single-node perfect intervention. In this work, we relax these assumptions and capitalize on the following observation: there often exists a subset of latents whose certain distributional properties (e.g., support, variance) remain stable across domains; this property holds when, for example, each domain comes from a multi-node imperfect intervention. Leveraging this observation, we show that autoencoders that incorporate such invariances can provably identify the stable set of latents from the rest across different settings.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

35 of 54 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  5. 2019Invariant Risk Minimizationcited by 1,854
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  7. 2020In Search of Lost Domain Generalizationcited by 1,054
  8. 2018Recognition in Terra Incognitacited by 658
  9. 2013Domain Generalization via Invariant Feature Representationcited by 623
  10. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  11. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  12. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
23 more
  1. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 282
  2. 2020Weakly-Supervised Disentanglement Without Compromisescited by 239
  3. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 160
  4. 2022Interventional Causal Representation Learningcited by 142
  5. 2022Weakly supervised causal representation learningcited by 140
  6. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 106
  7. 2020ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICAcited by 102
  8. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 98
  9. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  10. 2019The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICAcited by 86
  11. 2022Linear Causal Disentanglement via Interventionscited by 84
  12. 2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
  13. 2022Identifiability of deep generative models without auxiliary informationcited by 70
  14. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 65
  15. 2023Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolationcited by 58
  16. 2023Causal Component Analysiscited by 56
  17. 2023Score-based Causal Representation Learning with Interventionscited by 49
  18. 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
  19. 2023Provably Learning Object-Centric Representationscited by 45
  20. 2023Learning nonparametric latent causal graphs with unknown interventionscited by 34
  21. 2022DALL-E 2 Fails to Reliably Capture Common Syntactic Processescited by 31
  22. 2021Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learningcited by 30
  23. 2022Partial Disentanglement via Mechanism Sparsitycited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 6; 2025: 6; 2026: 9.

23 papers.

Sort:

By area:

  1. 2024A Sparsity Principle for Partially Observable Causal Representation Learningcited by 35
  2. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 31
  3. 2024Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Modelscited by 29
  4. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  5. 2023Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguitycited by 15
  6. 2024Linear Causal Representation Learning from Unknown Multi-node Interventionscited by 14
  7. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  8. 2024Identifiability Guarantees for Causal Disentanglement from Purely Observational Datacited by 7
  9. 2025From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?cited by 7
  10. 2025Sanity Checking Causal Representation Learning on a Simple Real-World Systemcited by 5
  11. 2025The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representationscited by 4
  12. 2025Measure-Theoretic Anti-Causal Representation Learningcited by 4
11 more
  1. 2026Content-Style Identification via Differential Independencecited by 2
  2. 2025Intervening to Learn and Compose Causally Disentangled Representationscited by 1
  3. 2026Beyond identifiability: Learning causal representations with few environments and finite samplescited by 1
  4. 2026Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixingcited by 1
  5. 2026Structure-agnostic Causal Representation Learningcited by 1
  6. 2025PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traitscited by 0
  7. 2026Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learningcited by 0
  8. 2026RECLAIM: Cyclic Causal Discovery Amid Measurement Noisecited by 0
  9. 2026Causal Learning with the Invariance Principlecited by 0
  10. 2026Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applicationscited by 0
  11. 2026Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shiftscited by 0