mlsanityData to 14 Oct 2026

Learning to Induce Causal Structure

arXiv 2204.04875 ↗First posted 11 Apr 2022stat.ML cs.LGcited by 68

Not on the map. Why?

Abstract (arXiv)

The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and evaluating them using either score-based methods (including continuous optimization) or independence tests. In our work, we instead treat the inference process as a black box and design a neural network architecture that learns the mapping from both observational and interventional data to graph structures via supervised training on synthetic graphs. The learned model generalizes to new synthetic graphs, is robust to train-test distribution shifts, and achieves state-of-the-art performance on naturalistic graphs for low sample complexity.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). Builds on 46 of its 86 references that are in the map. First posted on arXiv 11 Apr 2022.

Builds on

46 of 86 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  5. 2016Layer Normalizationcited by 5,669
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  7. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  8. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  9. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  10. 2021Transformers Can Do Bayesian Inferencecited by 360
  11. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  12. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
34 more
  1. 2019Gradient-Based Neural DAG Learningcited by 227
  2. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  3. 2013Learning Bayesian Networks: The Combination of Knowledge and Statistical Datacited by 187
  4. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 160
  5. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  6. 2019Causal Discovery with Reinforcement Learningcited by 145
  7. 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
  8. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  9. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  10. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 100
  11. 2021Coordination Among Neural Modules Through a Shared Global Workspacecited by 85
  12. 2017Causal Structure Learningcited by 84
  13. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  14. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  15. 2019Permutation-Based Causal Structure Learning with Unknown Intervention Targetscited by 69
  16. 2018Variational Autoencoder with Arbitrary Conditioningcited by 68
  17. 2016Structure Learning in Graphical Modelingcited by 66
  18. 2019Causal Discovery with General Non-Linear Relationships Using Non-Linear ICAcited by 58
  19. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  20. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  21. 2022Retrieval-Augmented Reinforcement Learningcited by 53
  22. 2021Learning Neural Causal Models with Active Interventionscited by 40
  23. 2020Active Invariant Causal Prediction: Experiment Selection through Stabilitycited by 37
  24. 2017Learning Causal Structures Using Regression Invariancecited by 32
  25. 2019Flow Models for Arbitrary Conditional Likelihoodscited by 30
  26. 2017Causal Generative Neural Networkscited by 24
  27. 2018Causal Inference via Kernel Deviance Measurescited by 22
  28. 2020Supervised Whole DAG Causal Discoverycited by 19
  29. 2020Amortized learning of neural causal representationscited by 14
  30. 2021ML4C: Seeing Causality Through Latent Vicinitycited by 11
  31. 2014The Randomized Causation Coefficientcited by 10
  32. 2017A Universal Marginalizer for Amortized Inference in Generative Modelscited by 9
  33. 2017Causal Inference by Stochastic Complexitycited by 3
  34. 2022BCDAG: An R package for Bayesian structure and Causal learning of Gaussian DAGscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 10; 2023: 10; 2024: 16; 2025: 9; 2026: 23.

68 papers.

Sort:

By area:

  1. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  2. 2023Supervised Pretraining Can Learn In-Context Reinforcement Learningcited by 139
  3. 2022Amortized Inference for Causal Structure Learningcited by 90
  4. 2025Do-PFN: In-Context Learning for Causal Effect Estimationcited by 51
  5. 2025CausalPFN: Amortized Causal Effect Estimation via In-Context Learningcited by 49
  6. 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
  7. 2024The Essential Role of Causality in Foundation World Models for Embodied AIcited by 32
  8. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  9. 2024A Meta-Learning Approach to Bayesian Causal Discoverycited by 22
  10. 2023Passive learning of active causal strategies in agents and language modelscited by 21
  11. 2024Sample, estimate, aggregate: A recipe for causal discovery foundation modelscited by 21
  12. 2022Deep Learning of Causal Structures in High Dimensionscited by 20
38 more
  1. 2022A Review of Causality for Learning Algorithms in Medical Image Analysiscited by 18
  2. 2024Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processescited by 18
  3. 2025Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learningcited by 13
  4. 2024Demystifying amortized causal discovery with transformerscited by 11
  5. 2023Discovering Mixtures of Structural Causal Models from Time Series Datacited by 10
  6. 2024Amortized Active Causal Induction with Deep Reinforcement Learningcited by 10
  7. 2024Score matching through the roof: linear, nonlinear, and latent variables causal discoverycited by 10
  8. 2022On the Generalization and Adaption Performance of Causal Modelscited by 8
  9. 2024A Fixed-Point Approach for Causal Generative Modelingcited by 7
  10. 2022Physics Informed Neural Network for Dynamic Stress Predictioncited by 6
  11. 2024Large-Scale Targeted Cause Discovery via Learning from Simulated Datacited by 6
  12. 2024Continuous Bayesian Model Selection for Multivariate Causal Discoverycited by 6
  13. 2026CauScale: Neural Causal Discovery at Scalecited by 6
  14. 2022Learning Latent Structural Causal Modelscited by 5
  15. 2025Does TabPFN Understand Causal Structures?cited by 5
  16. 2026Arrow: A Foundation Model for Causal Discoverycited by 5
  17. 2023Im-Promptu: In-Context Composition from Image Promptscited by 4
  18. 2023Shortcuts for causal discovery of nonlinear models by score matchingcited by 4
  19. 2024In-Context In-Context Learning with Transformer Neural Processescited by 4
  20. 2024Amortized Inference of Causal Models via Conditional Fixed-Point Iterationscited by 4
  21. 2023DiscoGen: Learning to Discover Gene Regulatory Networkscited by 3
  22. 2023Learned Causal Method Predictioncited by 3
  23. 2024Simulation-based Benchmarking for Causal Structure Learning in Gene Perturbation Experimentscited by 3
  24. 2025Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learningcited by 3
  25. 2025Meta-Statistical Learning: Supervised Learning of Statistical Estimatorscited by 3
  26. 2026MapPFN: Learning Causal Perturbation Maps in Contextcited by 3
  27. 2026FoundCause: Causal Discovery with Latent Confounders from Observational Datacited by 3
  28. 2022Learning domain-specific causal discovery from time seriescited by 2
  29. 2023Learning How to Infer Partial MDPs for In-Context Adaptation and Explorationcited by 2
  30. 2026Test-Time Learning of Causal Structure from Interventional Datacited by 2
  31. 2026A Knowledge-Informed Pretrained Model for Causal Discoverycited by 2
  32. 2026A Causal Foundation Model for Structure and Outcome Predictioncited by 2
  33. 2026CDFM: Towards a General-Purpose Causal Discovery Foundation Modelcited by 2
  34. 2026DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanismscited by 2
  35. 2022Causal Structural Hypothesis Testing and Data Generation Modelscited by 1
  36. 2024Identifying biological perturbation targets through causal differential networkscited by 1
  37. 2024LoSAM: Local Search in Additive Noise Models with Mixed Mechanisms and General Noise for Global Causal Discoverycited by 1
  38. 2025Amortized Conditional Independence Testingcited by 1

50 most cited of 68 All 68 (JSON)