mlsanityData to 7 Oct 2026

Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning

arXiv 2301.05169 ↗First posted 12 Jan 2023cs.LG cs.AI cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work. Our code and datasets will be available at https://sites.google.com/view/causaltriplet.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 12 Jan 2023.

Builds on

41 of 53 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2018World Modelscited by 1,444
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  5. 2020Object-Centric Learning with Slot Attentioncited by 865
  6. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  7. 2020Rescaling Egocentric Visioncited by 529
  8. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  9. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  10. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  11. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  12. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
29 more
  1. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  2. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  3. 2019Recurrent Independent Mechanismscited by 219
  4. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  5. 2021Towards Causal Representation Learningcited by 207
  6. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  7. 2022Weakly supervised causal representation learningcited by 140
  8. 2022Interventional Causal Representation Learningcited by 140
  9. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  10. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  11. 2017Neural Expectation Maximizationcited by 123
  12. 2020Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Codingcited by 121
  13. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  14. 2017Learning Independent Causal Mechanismscited by 104
  15. 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
  16. 2020On Disentangled Representations Learned From Correlated Datacited by 94
  17. 2018Variational Autoencoders Pursue PCA Directions (by Accident)cited by 84
  18. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  19. 2020A causal view of compositional zero-shot recognitioncited by 78
  20. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  21. 2020On the Transfer of Disentangled Representations in Realistic Settingscited by 63
  22. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  23. 2022Retrospectives on the Embodied AI Workshopcited by 46
  24. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  25. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  26. 2021ACRE: Abstract Causal REasoning Beyond Covariationcited by 30
  27. 2020Learning to Manipulate Individual Objects in an Imagecited by 22
  28. 2022Variational Causal Dynamics: Discovering Modular World Models from Interventionscited by 16
  29. 2022Towards a Grounded Theory of Causation for Embodied AIcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 9; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  2. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 30
  3. 2024The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applicationscited by 17
  4. 2023Object-Centric Multiple Object Trackingcited by 15
  5. 2024On the Identification of Temporally Causal Representation with Instantaneous Dependencecited by 15
  6. 2024Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Modelscited by 14
  7. 2024Compositional Risk Minimizationcited by 13
  8. 2025Are We Done with Object-Centric Learning?cited by 10
  9. 2025Sanity Checking Causal Representation Learning on a Simple Real-World Systemcited by 5
  10. 2023Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representationscited by 4
  11. 2024From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signalscited by 4
  12. 2025Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learningcited by 4
10 more
  1. 2025Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecastingcited by 3
  2. 2025Online Time Series Forecasting with Theoretical Guaranteescited by 2
  3. 2025State Combinatorial Generalization In Decision Making With Conditional Diffusion Modelscited by 1
  4. 2025Time Series Domain Adaptation via Latent Invariant Causal Mechanismcited by 1
  5. 2025Causal View of Time Series Imputation: Some Identification Results on Missing Mechanismcited by 1
  6. 2026Hierarchical Action Learning for Weakly-Supervised Action Segmentationcited by 1
  7. 2024Implicit Causal Representation Learning via Switchable Mechanismscited by 0
  8. 2024Disentangled Representations for Causal Cognitioncited by 0
  9. 2025Learning Robust Intervention Representations with Delta Embeddingscited by 0
  10. 2026Do-JEPA: From Masking to Intervention in Latent World Modelscited by 0