mlsanityData to 7 Oct 2026

BISCUIT: Causal Representation Learning from Binary Interactions

arXiv 2306.09643 ↗First posted 16 Jun 2023cs.LG cs.AI stat.MEcited by 38

Not on the map. Why?

Abstract (arXiv)

Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly interact with the environment and may implicitly perturb the behavior of some of these causal variables, often the targets it affects remain unknown. In this paper, we show that causal variables can still be identified for many common setups, e.g., additive Gaussian noise models, if the agent's interactions with a causal variable can be described by an unknown binary variable. This happens when each causal variable has two different mechanisms, e.g., an observational and an interventional one. Using this identifiability result, we propose BISCUIT, a method for simultaneously learning causal variables and their corresponding binary interaction variables. On three robotic-inspired datasets, BISCUIT accurately identifies causal variables and can even be scaled to complex, realistic environments for embodied AI.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

37 of 58 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2018Group Normalizationcited by 1,514
  9. 2020Mastering Atari with Discrete World Modelscited by 990
  10. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  11. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  12. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
25 more
  1. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  2. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
  3. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  4. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  5. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  6. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  7. 2022Weakly supervised causal representation learningcited by 140
  8. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  9. 2018State Representation Learning for Control: An Overviewcited by 125
  10. 2020Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Codingcited by 121
  11. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  12. 2020ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICAcited by 102
  13. 2021Independent mechanism analysis, a new concept?cited by 96
  14. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 96
  15. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  16. 2019Permutation-Based Causal Structure Learning with Unknown Intervention Targetscited by 69
  17. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  18. 2022Temporally Disentangled Representation Learningcited by 59
  19. 2019Causal Discovery with General Non-Linear Relationships Using Non-Linear ICAcited by 58
  20. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 50
  21. 2022Partial Disentanglement via Mechanism Sparsitycited by 29
  22. 2022Embrace the Gap: VAEs Perform Independent Mechanism Analysiscited by 28
  23. 2022Differentiable Causal Discovery Under Latent Interventionscited by 21
  24. 2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
  25. 2022Disentangling Mixtures of Unknown Causal Interventionscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 11; 2025: 10; 2026: 10.

38 papers.

Sort:

By area:

  1. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  2. 2024A Sparsity Principle for Partially Observable Causal Representation Learningcited by 34
  3. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 30
  4. 2024Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Modelscited by 29
  5. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  6. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  7. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  8. 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learningcited by 15
  9. 2023Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguitycited by 14
  10. 2024Linear Causal Representation Learning from Unknown Multi-node Interventionscited by 14
  11. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  12. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
26 more
  1. 2025Towards Interpretable Deep Generative Models via Causal Representation Learningcited by 12
  2. 2025Incorporating Hierarchical Semantics in Sparse Autoencoder Architecturescited by 12
  3. 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Researchcited by 9
  4. 2023Deep Backtracking Counterfactuals for Causally Compliant Explanationscited by 8
  5. 2024Language Agents Meet Causality -- Bridging LLMs and Causal World Modelscited by 8
  6. 2023Invariance & Causal Representation Learning: Prospects and Limitationscited by 5
  7. 2024Towards the Reusability and Compositionality of Causal Representationscited by 5
  8. 2025Sanity Checking Causal Representation Learning on a Simple Real-World Systemcited by 5
  9. 2025From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?cited by 5
  10. 2024CausalPlayground: Addressing Data-Generation Requirements in Cutting-Edge Causality Researchcited by 4
  11. 2024The Causal Information Bottleneck and Optimal Causal Variable Abstractionscited by 4
  12. 2025Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learningcited by 4
  13. 2025Curious Causality-Seeking Agents Learn Meta Causal Worldcited by 4
  14. 2026Structural Causal Bottleneck Modelscited by 4
  15. 2024CAnDOIT: Causal Discovery with Observational and Interventional Data from Time-Seriescited by 3
  16. 2025From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learningcited by 2
  17. 2026Self-Supervised Learning from Structural Invariancecited by 1
  18. 2026Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixingcited by 1
  19. 2025Learning Robust Intervention Representations with Delta Embeddingscited by 0
  20. 2026Disentangled Representation Learning through Unsupervised Symmetry Group Discoverycited by 0
  21. 2026Beyond identifiability: Learning causal representations with few environments and finite samplescited by 0
  22. 2026Diverse Dictionary Learningcited by 0
  23. 2026Concept Modulation Models: A Unified Framework for Identifiability and Extrapolationcited by 0
  24. 2026Towards Identifiable Representations under Misspecified Structurecited by 0
  25. 2026Identifying ODEs from Unstructured Data with Causal Representation Learningcited by 0
  26. 2026Do-JEPA: From Masking to Intervention in Latent World Modelscited by 0