mlsanityData to 7 Oct 2026

A Survey of Methods, Challenges and Perspectives in Causality

arXiv 2302.00293 ↗First posted 1 Feb 2023cs.LG stat.MEcited by 6

Not on the map. Why?

Abstract (arXiv)

Deep Learning models have shown success in a large variety of tasks by extracting correlation patterns from high-dimensional data but still struggle when generalizing out of their initial distribution. As causal engines aim to learn mechanisms independent from a data distribution, combining Deep Learning with Causality can have a great impact on the two fields. In this paper, we further motivate this assumption. We perform an extensive overview of the theories and methods for Causality from different perspectives, with an emphasis on Deep Learning and the challenges met by the two domains. We show early attempts to bring the fields together and the possible perspectives for the future. We finish by providing a large variety of applications for techniques from Causality.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 87 of its 227 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

87 of 227 references.

References · 87

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  10. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  11. 2018World Modelscited by 1,444
  12. 2016Variational Graph Auto-Encoderscited by 1,373
38 more
  1. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  2. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  3. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  4. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
  5. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  6. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  7. 2018Disentangling by Factorisingcited by 614
  8. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  9. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 475
  10. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  11. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  12. 2018Towards a Definition of Disentangled Representationscited by 294
  13. 2019Causal Confusion in Imitation Learningcited by 286
  14. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  15. 2017Detecting causal associations in large nonlinear time series datasetscited by 240
  16. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  17. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  18. 2019Recurrent Independent Mechanismscited by 219
  19. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 213
  20. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  21. 2018Neural Autoregressive Flowscited by 207
  22. 2020A Survey on Causal Inferencecited by 202
  23. 2013Causal Inference and Causal Explanation with Background Knowledgecited by 168
  24. 2019Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changescited by 166
  25. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  26. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  27. 2016Foundations of Structural Causal Models with Cycles and Latent Variablescited by 134
  28. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  29. 2020Interventional Few-Shot Learningcited by 112
  30. 2021Causal Attention for Vision-Language Taskscited by 111
  31. 2019Domain Agnostic Learning with Disentangled Representationscited by 107
  32. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  33. 2022Causal Machine Learning: A Survey and Open Problemscited by 107
  34. 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
  35. 2020Causal Autoregressive Flowscited by 97
  36. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  37. 2021Independent mechanism analysis, a new concept?cited by 96
  38. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 1.

6 papers.

  1. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 52
  2. 2024Can Large Language Models Learn Independent Causal Mechanisms?cited by 3
  3. 2024AILS-NTUA at SemEval-2024 Task 9: Cracking Brain Teasers: Transformer Models for Lateral Thinking Puzzlescited by 1
  4. 2024Chatbots and Zero Sales Resistancecited by 0
  5. 2024Robust Domain Generalisation with Causal Invariant Bayesian Neural Networkscited by 0
  6. 2025Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worldscited by 0