mlsanityData to 7 Oct 2026

Deep Causal Learning: Representation, Discovery and Inference

arXiv 2211.03374 ↗First posted 7 Nov 2022cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Causal learning has garnered significant attention in recent years because it reveals the essential relationships that underpin phenomena and delineates the mechanisms by which the world evolves. Nevertheless, traditional causal learning methods face numerous challenges and limitations, including high-dimensional, unstructured variables, combinatorial optimization problems, unobserved confounders, selection biases, and estimation inaccuracies. Deep causal learning, which leverages deep neural networks, offers innovative insights and solutions for addressing these challenges. Although numerous deep learning-based methods for causal discovery and inference have been proposed, there remains a dearth of reviews examining the underlying mechanisms by which deep learning can enhance causal learning. In this article, we comprehensively review how deep learning can contribute to causal learning by tackling traditional challenges across three key dimensions: representation, discovery, and inference. We emphasize that deep causal learning is pivotal for advancing the theoretical frontiers and broadening the practical applications of causal science. We conclude by summarizing open issues and outlining potential directions for future research.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 119 of its 254 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

119 of 254 references.

References · 119

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2016Variational Graph Auto-Encoderscited by 1,373
  7. 2019An Introduction to Variational Autoencoderscited by 997
  8. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  9. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 597
  10. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  11. 2016Tutorial on Variational Autoencoderscited by 404
  12. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
38 more
  1. 2016Learning Representations for Counterfactual Inferencecited by 327
  2. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 285
  3. 2019Causality for Machine Learningcited by 242
  4. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  5. 2019Gradient-Based Neural DAG Learningcited by 227
  6. 2020Domain Generalization using Causal Matchingcited by 224
  7. 2018Gender Bias in Neural Natural Language Processingcited by 210
  8. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  9. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  10. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  11. 2020A Survey on Causal Inferencecited by 202
  12. 2019Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changescited by 166
  13. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  14. 2020Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representationscited by 154
  15. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  16. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 150
  17. 2019Causal Discovery with Reinforcement Learningcited by 145
  18. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  19. 2021Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Modelscited by 127
  20. 2016Learning in Implicit Generative Modelscited by 124
  21. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  22. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  23. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 112
  24. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  25. 2022Causal Machine Learning: A Survey and Open Problemscited by 107
  26. 2017Learning Independent Causal Mechanismscited by 104
  27. 2020ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICAcited by 102
  28. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 99
  29. 2020Causal Autoregressive Flowscited by 97
  30. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  31. 2021Learning Temporally Causal Latent Processes from General Temporal Datacited by 96
  32. 2022Deep End-to-end Causal Inferencecited by 93
  33. 2019Learning Counterfactual Representations for Estimating Individual Dose-Response Curvescited by 90
  34. 2022Amortized Inference for Causal Structure Learningcited by 89
  35. 2017Causal Structure Learningcited by 84
  36. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  37. 2020Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networkscited by 78
  38. 2020Causal Discovery in Physical Systems from Videoscited by 77

50 most cited of 119 All 119 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 3; 2026: 6.

11 papers.

  1. 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
  2. 2025CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Datacited by 7
  3. 2025Revealing Multimodal Causality with Large Language Modelscited by 3
  4. 2023CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationshipscited by 1
  5. 2026CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detectioncited by 1
  6. 2025Noise-robust Contrastive Learning for Critical Transition Detection in Dynamical Systemscited by 0
  7. 2026PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discoverycited by 0
  8. 2026Debiased Multimodal Personality Understanding through Dual Causal Interventioncited by 0
  9. 2026GS-FUSE: Granger-Supervised Gated Fusion and Multi-Granularity Alignment for Event-Driven Financial Forecastingcited by 0
  10. 2026Embedded Polygon Symbolic Transfer Entropy (EPSTE): A Geometric Token and Deep Learning Approach to Estimating Transfer Entropy in Neuroimaging Time Seriescited by 0
  11. 2026Resilient Concurrent Causal Discovery for Topological Event Sequencescited by 0