mlsanityData to 7 Oct 2026

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

arXiv 2206.06169 ↗First posted 13 Jun 2022cs.LG cs.AI stat.MLcited by 50

Not on the map. Why?

Abstract (arXiv)

Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has shown that one can reconstruct the causal variables from temporal sequences of observations under the assumption that there are no instantaneous causal relations between them. In practical applications, however, our measurement or frame rate might be slower than many of the causal effects. This effectively creates "instantaneous" effects and invalidates previous identifiability results. To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e.g., as actions of an agent. iCITRIS identifies the potentially multidimensional causal variables from temporal observations, while simultaneously using a differentiable causal discovery method to learn their causal graph. In experiments on three datasets of interactive systems, iCITRIS accurately identifies the causal variables and their causal graph.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 43 of its 79 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

43 of 79 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  9. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  10. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  11. 2020Object-Centric Learning with Slot Attentioncited by 865
  12. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
31 more
  1. 2018MINE: Mutual Information Neural Estimationcited by 680
  2. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  3. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  4. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  5. 2019Causal Confusion in Imitation Learningcited by 286
  6. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  7. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
  8. 2021Conditional Object-Centric Learning from Videocited by 247
  9. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  10. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  11. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  12. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  13. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  14. 2021Towards Causal Representation Learningcited by 207
  15. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  16. 2022Weakly supervised causal representation learningcited by 140
  17. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  18. 2020Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Codingcited by 121
  19. 2021Independent mechanism analysis, a new concept?cited by 96
  20. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 96
  21. 2020On Disentangled Representations Learned From Correlated Datacited by 94
  22. 2020Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)cited by 91
  23. 2019Masked Gradient-Based Causal Structure Learningcited by 89
  24. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  25. 2020SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flowscited by 71
  26. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 70
  27. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  28. 2019Causal Discovery with General Non-Linear Relationships Using Non-Linear ICAcited by 58
  29. 2019Disentangling Factors of Variation Using Few Labelscited by 57
  30. 2022Embrace the Gap: VAEs Perform Independent Mechanism Analysiscited by 28
  31. 2022Learning Latent Causal Dynamicscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 12; 2024: 12; 2025: 11; 2026: 12.

50 papers.

Sort:

By area:

  1. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  2. 2023Causal Component Analysiscited by 56
  3. 2023BISCUIT: Causal Representation Learning from Binary Interactionscited by 38
  4. 2023General Identifiability and Achievability for Causal Representation Learningcited by 34
  5. 2023Causal Representation Learning Made Identifiable by Grouping of Observational Variablescited by 30
  6. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 30
  7. 2023Learning World Models with Identifiable Factorizationcited by 23
  8. 2024Marrying Causal Representation Learning with Dynamical Systems for Sciencecited by 22
  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. 2024Interaction Asymmetry: A General Principle for Learning Composable Abstractionscited by 19
  12. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
38 more
  1. 2024The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applicationscited by 17
  2. 2022Variational Causal Dynamics: Discovering Modular World Models from Interventionscited by 16
  3. 2024On the Identification of Temporally Causal Representation with Instantaneous Dependencecited by 15
  4. 2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
  5. 2024Linear Causal Representation Learning from Unknown Multi-node Interventionscited by 14
  6. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  7. 2024Causal Temporal Representation Learning with Nonstationary Sparse Transitioncited by 12
  8. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  9. 2023On the Identifiability of Switching Dynamical Systemscited by 9
  10. 2025Towards Identifiability of Hierarchical Temporal Causal Representation Learningcited by 7
  11. 2025Learning General Causal Structures with Hidden Dynamic Process for Climate Analysiscited by 6
  12. 2025Debiasing Reward Models by Representation Learning with Guaranteescited by 6
  13. 2023Invariance & Causal Representation Learning: Prospects and Limitationscited by 5
  14. 2024Towards the Reusability and Compositionality of Causal Representationscited by 5
  15. 2024Towards Identifiable Latent Additive Noise Modelscited by 5
  16. 2025Sanity Checking Causal Representation Learning on a Simple Real-World Systemcited by 5
  17. 2025The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representationscited by 4
  18. 2025LLM Interpretability with Identifiable Temporal-Instantaneous Representationcited by 4
  19. 2026Structural Causal Bottleneck Modelscited by 4
  20. 2026What Makes a Representation Good for Single-Cell Perturbation Prediction?cited by 3
  21. 2025Controllable Video Generation with Provable Disentanglementcited by 2
  22. 2025From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learningcited by 2
  23. 2026Causal Representation Meets Stochastic Modeling under Generic Geometrycited by 2
  24. 2026Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learningcited by 2
  25. 2026A General Representation-Based Approach to Multi-Source Domain Adaptationcited by 2
  26. 2022Identifying Unique Spatial-Temporal Bayesian Network without Markov Equivalencecited by 1
  27. 2024Identifiable Representation and Model Learning for Latent Dynamic Systemscited by 1
  28. 2024Discovering Latent Causal Graphs from Spatiotemporal Datacited by 1
  29. 2025Learning Causal Response Representations through Direct Effect Analysiscited by 1
  30. 2025Towards Causal Representation Learning with Observable Sources as Auxiliariescited by 1
  31. 2026Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Predictioncited by 1
  32. 2025Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shiftcited by 0
  33. 2026FlexCausal: Flexible Causal Disentanglement via Structural Flow Priors and Manifold-Aware Interventionscited by 0
  34. 2026A Closer Look at the Application of Causal Inference in Graph Representation Learningcited by 0
  35. 2026Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applicationscited by 0
  36. 2026Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shiftscited by 0
  37. 2026Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent Statescited by 0
  38. 2026Abductive World Modeling via Causal Representation Learningcited by 0