mlsanityData to 7 Oct 2026

Learning Neural Causal Models from Unknown Interventions

arXiv 1910.01075 ↗First posted 2 Oct 2019stat.ML cs.AI cs.LGcited by 113

Not on the map. Why?

Abstract (arXiv)

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data. However, there are theoretical limitations on the identifiability of underlying structures obtained from observational data alone. Interventional data provides much richer information about the underlying data-generating process. However, the extension and application of methods designed for observational data to include interventions is not straightforward and remains an open problem. In this paper we provide a general framework based on continuous optimization and neural networks to create models for the combination of observational and interventional data. The proposed method is even applicable in the challenging and realistic case that the identity of the intervened upon variable is unknown. We examine the proposed method in the setting of graph recovery both de novo and from a partially-known edge set. We establish strong benchmark results on several structure learning tasks, including structure recovery of both synthetic graphs as well as standard graphs from the Bayesian Network Repository.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 38; 2023: 15; 2024: 19; 2025: 15; 2026: 6.

113 papers.

Sort:

By area:

  1. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  2. 2021Towards Causal Representation Learningcited by 207
  3. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  4. 2021DiBS: Differentiable Bayesian Structure Learningcited by 105
  5. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 96
  6. 2022Amortized Inference for Causal Structure Learningcited by 89
  7. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  8. 2023Modular Deep Learningcited by 82
  9. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 70
  10. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  11. 2022Temporally Disentangled Representation Learningcited by 59
  12. 2022Diversify and Disambiguate: Learning From Underspecified Datacited by 55
38 more
  1. 2022Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesiscited by 54
  2. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  3. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  4. 2022Interventions, Where and How? Experimental Design for Causal Models at Scalecited by 49
  5. 2022Causal Structure Learning: a Combinatorial Perspectivecited by 46
  6. 2021Variational Causal Networks: Approximate Bayesian Inference over Causal Structurescited by 43
  7. 2021Learning Neural Causal Models with Active Interventionscited by 40
  8. 2021Fast and Slow Learning of Recurrent Independent Mechanismscited by 36
  9. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  10. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  11. 2024The Essential Role of Causality in Foundation World Models for Embodied AIcited by 32
  12. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  13. 2022CausalBench: A Large-scale Benchmark for Network Inference from Single-cell Perturbation Datacited by 29
  14. 2023DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNetscited by 27
  15. 2022BaCaDI: Bayesian Causal Discovery with Unknown Interventionscited by 26
  16. 2023The Relational Bottleneck as an Inductive Bias for Efficient Abstractioncited by 26
  17. 2022Causality-driven Hierarchical Structure Discovery for Reinforcement Learningcited by 23
  18. 2021Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Modelscited by 22
  19. 2022Differentiable Causal Discovery Under Latent Interventionscited by 21
  20. 2022Deep Learning of Causal Structures in High Dimensionscited by 20
  21. 2024Position: Understanding LLMs Requires More Than Statistical Generalizationcited by 20
  22. 2022Offline Reinforcement Learning with Causal Structured World Modelscited by 19
  23. 2021GeneDisco: A Benchmark for Experimental Design in Drug Discoverycited by 18
  24. 2024Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processescited by 18
  25. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  26. 2021Structured Sparsity Inducing Adaptive Optimizers for Deep Learningcited by 17
  27. 2021FedDAG: Federated DAG Structure Learningcited by 17
  28. 2025Causally Reliable Concept Bottleneck Modelscited by 17
  29. 2022Variational Causal Dynamics: Discovering Modular World Models from Interventionscited by 16
  30. 2022On the link between conscious function and general intelligence in humans and machinescited by 15
  31. 2022Towards efficient representation identification in supervised learningcited by 14
  32. 2022Learning Latent Causal Dynamicscited by 13
  33. 2024ADAM: An Embodied Causal Agent in Open-World Environmentscited by 13
  34. 2022Characterization and Greedy Learning of Gaussian Structural Causal Models under Unknown Interventionscited by 12
  35. 2023Generative Causal Representation Learning for Out-of-Distribution Motion Forecastingcited by 12
  36. 2024Mitigating attribute amplification in counterfactual image generationcited by 12
  37. 2022A Meta-Reinforcement Learning Algorithm for Causal Discoverycited by 11
  38. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11

50 most cited of 113 All 113 (JSON)