mlsanityData to 7 Oct 2026

Avoiding Discrimination through Causal Reasoning

arXiv 1706.02744 ↗First posted 8 Jun 2017stat.ML cs.CY cs.LGcited by 191

Not on the map. Why?

Abstract (arXiv)

Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. Most of these criteria are observational: They depend only on the joint distribution of predictor, protected attribute, features, and outcome. While convenient to work with, observational criteria have severe inherent limitations that prevent them from resolving matters of fairness conclusively. Going beyond observational criteria, we frame the problem of discrimination based on protected attributes in the language of causal reasoning. This viewpoint shifts attention from "What is the right fairness criterion?" to "What do we want to assume about the causal data generating process?" Through the lens of causality, we make several contributions. First, we crisply articulate why and when observational criteria fail, thus formalizing what was before a matter of opinion. Second, our approach exposes previously ignored subtleties and why they are fundamental to the problem. Finally, we put forward natural causal non-discrimination criteria and develop algorithms that satisfy them.

Key facts. Cited by 191 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 42; 2022: 46; 2023: 37; 2024: 31; 2025: 21; 2026: 14.

191 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2021Towards Causal Representation Learningcited by 207
  3. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  4. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  5. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
  6. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  7. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  8. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  9. 2021Trustworthy AI: A Computational Perspectivecited by 93
  10. 2022Synthetic Data -- what, why and how?cited by 66
  11. 2021Fairness via Representation Neutralizationcited by 63
  12. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
38 more
  1. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  2. 2021Agent Incentives: A Causal Perspectivecited by 51
  3. 2021Sample Selection for Fair and Robust Trainingcited by 48
  4. 2022From Statistical to Causal Learningcited by 40
  5. 2021Personalized Counterfactual Fairness in Recommendationcited by 38
  6. 2022Causal Conceptions of Fairness and their Consequencescited by 38
  7. 2022Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal Viewcited by 31
  8. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  9. 2021Fairness in Ranking under Uncertaintycited by 27
  10. 2022Stochastic Causal Programming for Bounding Treatment Effectscited by 25
  11. 2021UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Modelscited by 23
  12. 2022Marrying Fairness and Explainability in Supervised Learningcited by 23
  13. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23
  14. 2021Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systemscited by 20
  15. 2022Fairness Amidst Non-IID Graph Data: A Literature Reviewcited by 20
  16. 2022Counterfactual Fairness with Partially Known Causal Graphcited by 20
  17. 2022Improvement-Focused Causal Recourse (ICR)cited by 20
  18. 2024Prompting Fairness: Integrating Causality to Debias Large Language Modelscited by 20
  19. 2021Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloudcited by 19
  20. 2021FairMask: Better Fairness via Model-based Rebalancing of Protected Attributescited by 19
  21. 2024Auditing the Use of Language Models to Guide Hiring Decisionscited by 19
  22. 2021A Framework for Fairness: A Systematic Review of Existing Fair AI Solutionscited by 18
  23. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  24. 2023Improving Recommendation Fairness via Data Augmentationcited by 18
  25. 2021Removing biased data to improve fairness and accuracycited by 17
  26. 2021Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decompositioncited by 17
  27. 2022Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributescited by 17
  28. 2021fairadapt: Causal Reasoning for Fair Data Pre-processingcited by 16
  29. 2022Selection, Ignorability and Challenges With Causal Fairnesscited by 16
  30. 2022Causal Discovery for Fairnesscited by 16
  31. 2023Fairness through Aleatoric Uncertaintycited by 16
  32. 2023Challenges of Large Language Models for Mental Health Counselingcited by 16
  33. 2022Backtracking Counterfactualscited by 15
  34. 2024Utility-Fairness Trade-Offs and How to Find Themcited by 15
  35. 2023Improving Fair Training under Correlation Shiftscited by 14
  36. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  37. 2021Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classificationcited by 13
  38. 2021Disentangled Representations from Non-Disentangled Modelscited by 13

50 most cited of 191 All 191 (JSON)