mlsanityData to 14 Oct 2026

A Graph Autoencoder Approach to Causal Structure Learning

arXiv 1911.07420 ↗First posted 18 Nov 2019cs.LG stat.MLcited by 55

Not on the map. Why?

Abstract (arXiv)

Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed the combinatorial structure learning problem into a continuous one and then solved it using gradient-based optimization methods. Following the recent state-of-the-arts, we propose a new gradient-based method to learn causal structures from observational data. The proposed method generalizes the recent gradient-based methods to a graph autoencoder framework that allows nonlinear structural equation models and is easily applicable to vector-valued variables. We demonstrate that on synthetic datasets, our proposed method outperforms other gradient-based methods significantly, especially on large causal graphs. We further investigate the scalability and efficiency of our method, and observe a near linear training time when scaling up the graph size.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 5; 2023: 15; 2024: 5; 2025: 11; 2026: 8.

55 papers.

Sort:

By area:

  1. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 211
  2. 2021DiBS: Differentiable Bayesian Structure Learningcited by 106
  3. 2022Deep End-to-end Causal Inferencecited by 95
  4. 2021gCastle: A Python Toolbox for Causal Discoverycited by 61
  5. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  6. 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
  7. 2021Learning Neural Causal Models with Active Interventionscited by 40
  8. 2023A Survey on Causal Discovery Methods for I.I.D. and Time Series Datacited by 35
  9. 2021Towards Federated Bayesian Network Structure Learning with Continuous Optimizationcited by 31
  10. 2021FedDAG: Federated DAG Structure Learningcited by 17
  11. 2024Ordering-Based Causal Discovery for Linear and Nonlinear Relationscited by 13
  12. 2024Recursive Causal Discoverycited by 12
38 more
  1. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  2. 2023Causality-based CTR Prediction using Graph Neural Networkscited by 9
  3. 2023Achieving Counterfactual Fairness for Anomaly Detectioncited by 7
  4. 2022On Root Cause Localization and Anomaly Mitigation through Causal Inferencecited by 6
  5. 2021On the Role of Entropy-based Loss for Learning Causal Structures with Continuous Optimizationcited by 5
  6. 2023Boosting Differentiable Causal Discovery via Adaptive Sample Reweightingcited by 5
  7. 2023Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networkscited by 5
  8. 2021Causal Inference in medicine and in health policy, a summarycited by 4
  9. 2023Discovering Dynamic Causal Space for DAG Structure Learningcited by 4
  10. 2024Causal Inference with Latent Variables: Recent Advances and Future Prospectivescited by 4
  11. 2025The Robustness of Differentiable Causal Discovery in Misspecified Scenarioscited by 4
  12. 2022Do-Operation Guided Causal Representation Learning with Reduced Supervision Strengthcited by 3
  13. 2022Learning Discrete Directed Acyclic Graphs via Backpropagationcited by 3
  14. 2023Knowledge Guided Representation Learning and Causal Structure Learning in Soil Sciencecited by 3
  15. 2023Shadow Datasets, New challenging datasets for Causal Representation Learningcited by 3
  16. 2025ACCESS : A Benchmark for Abstract Causal Event Discovery and Reasoningcited by 3
  17. 2021Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicinecited by 2
  18. 2023Directed Acyclic Graphs With Tearscited by 2
  19. 2026Test-Time Learning of Causal Structure from Interventional Datacited by 2
  20. 2026A Knowledge-Informed Pretrained Model for Causal Discoverycited by 2
  21. 2023Learning Personalized Brain Functional Connectivity of MDD Patients from Multiple Sites via Federated Bayesian Networkscited by 1
  22. 2023Recovering Linear Causal Models with Latent Variables via Cholesky Factorization of Covariance Matrixcited by 1
  23. 2023A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representationscited by 1
  24. 2023Multi-granularity Causal Structure Learningcited by 1
  25. 2024DiffusionCounterfactuals: Inferring High-dimensional Counterfactuals with Guidance of Causal Representationscited by 1
  26. 2025Toward Temporal Causal Representation Learning with Tensor Decompositioncited by 1
  27. 2021GAETS: A Graph Autoencoder Time Series Approach Towards Battery Parameter Estimationcited by 0
  28. 2023Spatial-Temporal DAG Convolutional Networks for End-to-End Joint Effective Connectivity Learning and Resting-State fMRI Classificationcited by 0
  29. 2024Scalable Temporal Anomaly Causality Discovery in Large Systems: Achieving Computational Efficiency with Binary Anomaly Flag Datacited by 0
  30. 2025Graph Pseudotime Analysis and Neural Stochastic Differential Equations for Analyzing Retinal Degeneration Dynamics and Beyondcited by 0
  31. 2025From Observations to Causations: A GNN-based Probabilistic Prediction Framework for Causal Discoverycited by 0
  32. 2025TempOpt -- Unsupervised Alarm Relation Learning for Telecommunication Networkscited by 0
  33. 2025Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detectioncited by 0
  34. 2025GCVAMD: A Modified CausalVAE Model for Causal Age-related Macular Degeneration Risk Factor Detection and Predictioncited by 0
  35. 2025Shylock: Causal Discovery in Multivariate Time Series based on Hybrid Constraintscited by 0
  36. 2025Importance Ranking in Complex Networks via Influence-aware Causal Node Embeddingcited by 0
  37. 2025LightHCG: a Lightweight yet powerful HSIC Disentanglement based Causal Glaucoma Detection Model frameworkcited by 0
  38. 2026LungCRCT: Causal Representation based Lung CT Processing for Lung Cancer Treatmentcited by 0

50 most cited of 55 All 55 (JSON)