mlsanityData to 7 Oct 2026

Linear Causal Representation Learning from Unknown Multi-node Interventions

arXiv 2406.05937 ↗First posted 9 Jun 2024cs.LG stat.MLcited by 14

Not on the map. Why?

Abstract (arXiv)

Despite the multifaceted recent advances in interventional causal representation learning (CRL), they primarily focus on the stylized assumption of single-node interventions. This assumption is not valid in a wide range of applications, and generally, the subset of nodes intervened in an interventional environment is fully unknown. This paper focuses on interventional CRL under unknown multi-node (UMN) interventional environments and establishes the first identifiability results for general latent causal models (parametric or nonparametric) under stochastic interventions (soft or hard) and linear transformation from the latent to observed space. Specifically, it is established that given sufficiently diverse interventional environments, (i) identifiability up to ancestors is possible using only soft interventions, and (ii) perfect identifiability is possible using hard interventions. Remarkably, these guarantees match the best-known results for more restrictive single-node interventions. Furthermore, CRL algorithms are also provided that achieve the identifiability guarantees. A central step in designing these algorithms is establishing the relationships between UMN interventional CRL and score functions associated with the statistical models of different interventional environments. Establishing these relationships also serves as constructive proof of the identifiability guarantees.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 9 Jun 2024.

Builds on

28 of 39 references.

References · 28

  1. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  2. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  3. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  4. 2022Weakly supervised causal representation learningcited by 140
  5. 2022Interventional Causal Representation Learningcited by 140
  6. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  7. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  8. 2022Linear Causal Disentanglement via Interventionscited by 84
  9. 2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
  10. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 72
  11. 2019Permutation-Based Causal Structure Learning with Unknown Intervention Targetscited by 69
  12. 2024Causal Representation Learning from Multiple Distributions: A General Settingcited by 67
16 more
  1. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 50
  2. 2023Score-based Causal Representation Learning with Interventionscited by 49
  3. 2024Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependenciescited by 39
  4. 2023BISCUIT: Causal Representation Learning from Binary Interactionscited by 38
  5. 2023Learning nonparametric latent causal graphs with unknown interventionscited by 34
  6. 2023General Identifiability and Achievability for Causal Representation Learningcited by 34
  7. 2023Unpaired Multi-Domain Causal Representation Learningcited by 32
  8. 2023Causal Representation Learning Made Identifiable by Grouping of Observational Variablescited by 30
  9. 2024Score-based Causal Representation Learning: Linear and General Transformationscited by 27
  10. 2023Multi-Domain Causal Representation Learning via Weak Distributional Invariancescited by 23
  11. 2023Identifiable Latent Polynomial Causal Models Through the Lens of Changecited by 23
  12. 2020Nonparametric Score Estimatorscited by 22
  13. 2023Causal machine learning for single-cell genomicscited by 22
  14. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  15. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  16. 2023Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguitycited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 8.

14 papers.

Sort:

By area:

  1. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 30
  2. 2025Debiasing Reward Models by Representation Learning with Guaranteescited by 6
  3. 2026Causal Representation Learning from General Environments under Nonparametric Mixingcited by 4
  4. 2026Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attentioncited by 3
  5. 2026Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learningcited by 2
  6. 2026A General Representation-Based Approach to Multi-Source Domain Adaptationcited by 2
  7. 2026Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolatecited by 1
  8. 2025Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shiftcited by 0
  9. 2025Learning Robust Intervention Representations with Delta Embeddingscited by 0
  10. 2025Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglementcited by 0
  11. 2025ROPES: Robotic Pose Estimation via Score-Based Causal Representation Learningcited by 0
  12. 2026CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularizationcited by 0
2 more
  1. 2026Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applicationscited by 0
  2. 2026Concept Modulation Models: A Unified Framework for Identifiability and Extrapolationcited by 0