mlsanityData to 7 Oct 2026

Causal Deep Learning

arXiv 2303.02186 ↗First posted 3 Mar 2023cs.LG cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential largely remains to be unlocked as causality often requires crucial assumptions which cannot be tested in practice. To address this challenge, we propose a new way of thinking about causality -- we call this causal deep learning. Our causal deep learning framework spans three dimensions: (1) a structural dimension, which incorporates partial yet testable causal knowledge rather than assuming either complete or no causal knowledge among the variables of interest; (2) a parametric dimension, which encompasses parametric forms that capture the type of relationships among the variables of interest; and (3) a temporal dimension, which captures exposure times or how the variables of interest interact (possibly causally) over time. Causal deep learning enables us to make progress on a variety of real-world problems by leveraging partial causal knowledge (including independencies among variables) and quantitatively characterising causal relationships among variables of interest (possibly over time). Our framework clearly identifies which assumptions are testable and which ones are not, such that the resulting solutions can be judiciously adopted in practice. Using our formulation we can combine or chain together causal representations to solve specific problems without losing track of which assumptions are required to build these solutions, pushing real-world impact in healthcare, economics and business, environmental sciences and education, through causal deep learning.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 77 of its 170 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

77 of 170 references.

References · 77

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Counterfactual Fairnesscited by 802
  3. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  4. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  5. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  6. 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
  7. 2013Causal Discovery with Continuous Additive Noise Modelscited by 252
  8. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  9. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  10. 2019Learning Sparse Nonparametric DAGscited by 207
  11. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 156
  12. 2020Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representationscited by 154
38 more
  1. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  2. 2019Causal Discovery with Reinforcement Learningcited by 145
  3. 2018Invariance, Causality and Robustnesscited by 123
  4. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  5. 2021Counterfactual Generative Networkscited by 111
  6. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  7. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  8. 2022Causal Machine Learning: A Survey and Open Problemscited by 107
  9. 2016Causal Bandits: Learning Good Interventions via Causal Inferencecited by 100
  10. 2020Causal Interpretability for Machine Learning -- Problems, Methods and Evaluationcited by 82
  11. 2021On Inductive Biases for Heterogeneous Treatment Effect Estimationcited by 74
  12. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 70
  13. 2019PC-Fairness: A Unified Framework for Measuring Causality-based Fairnesscited by 67
  14. 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 67
  15. 2017Invariant Causal Prediction for Sequential Datacited by 63
  16. 2018Graphical Models for Processing Missing Datacited by 57
  17. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  18. 2019Causal Reasoning from Meta-reinforcement Learningcited by 53
  19. 2018Causal Reasoning for Algorithmic Fairnesscited by 51
  20. 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 50
  21. 2020Generative Interventions for Causal Learningcited by 45
  22. 2013Strong Completeness and Faithfulness in Bayesian Networkscited by 44
  23. 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
  24. 2020Provably Efficient Causal Reinforcement Learning with Confounded Observational Datacited by 40
  25. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  26. 2020Causal Bayesian Optimizationcited by 39
  27. 2020Budgeted and Non-budgeted Causal Banditscited by 38
  28. 2021Causal Reinforcement Learning using Observational and Interventional Datacited by 38
  29. 2021Causal Bandits with Unknown Graph Structurecited by 37
  30. 2019PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systemscited by 35
  31. 2020Causal models for dynamical systemscited by 34
  32. 2020Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Frameworkcited by 29
  33. 2020Causality Learning: A New Perspective for Interpretable Machine Learningcited by 28
  34. 2022On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challengescited by 28
  35. 2016Contextual Bandits with Latent Confounders: An NMF Approachcited by 26
  36. 2020Invariant Representation Learning for Treatment Effect Estimationcited by 25
  37. 2017Causal Generative Neural Networkscited by 24
  38. 2020Bandits with Partially Observable Confounded Datacited by 22

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 8; 2025: 6.

20 papers.

Sort:

By area:

  1. 2024The Essential Role of Causality in Foundation World Models for Embodied AIcited by 32
  2. 2023The role of causality in explainable artificial intelligencecited by 17
  3. 2024CausalEval: Towards Better Causal Reasoning in Language Modelscited by 13
  4. 2024ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inferencecited by 12
  5. 2024NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrativecited by 10
  6. 2023Causality-Driven One-Shot Learning for Prostate Cancer Grading from MRIcited by 6
  7. 2025An AI-powered Bayesian generative modeling approach for causal inference in observational studiescited by 6
  8. 2024Causality from Bottom to Top: A Surveycited by 5
  9. 2023Learned Causal Method Predictioncited by 3
  10. 2025Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Modelscited by 2
  11. 2023Do Not Marginalize Mechanisms, Rather Consolidate!cited by 1
  12. 2023CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationshipscited by 1
8 more
  1. 2023Enhancing the Performance of Neural Networks Through Causal Discovery and Integration of Domain Knowledgecited by 1
  2. 2024DAGnosis: Localized Identification of Data Inconsistencies using Structurescited by 1
  3. 2025Causal Graph Neural Networks for Healthcarecited by 1
  4. 2024Disentangled Representations for Causal Cognitioncited by 0
  5. 2024MSCT: Addressing Time-Varying Confounding with Marginal Structural Causal Transformer for Counterfactual Post-Crash Traffic Predictioncited by 0
  6. 2025Integrating Causality with Neurochaos Learning: Proposed Approach and Research Agendacited by 0
  7. 2025Generative Learner for Distributional Causal Effectscited by 0
  8. 2025Shape Modeling of Longitudinal Medical Images: From Diffeomorphic Metric Mapping to Deep Learningcited by 0