mlsanityData to 7 Oct 2026

A causal framework for discovering and removing direct and indirect discrimination

arXiv 1611.07509 ↗First posted 22 Nov 2016cs.LGcited by 71

Not on the map. Why?

Abstract (arXiv)

Anti-discrimination is an increasingly important task in data science. In this paper, we investigate the problem of discovering both direct and indirect discrimination from the historical data, and removing the discriminatory effects before the data is used for predictive analysis (e.g., building classifiers). We make use of the causal network to capture the causal structure of the data. Then we model direct and indirect discrimination as the path-specific effects, which explicitly distinguish the two types of discrimination as the causal effects transmitted along different paths in the network. Based on that, we propose an effective algorithm for discovering direct and indirect discrimination, as well as an algorithm for precisely removing both types of discrimination while retaining good data utility. Different from previous works, our approaches can ensure that the predictive models built from the modified data will not incur discrimination in decision making. Experiments using real datasets show the effectiveness of our approaches.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 21; 2023: 9; 2024: 14; 2025: 7; 2026: 3.

71 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  3. 2021Trustworthy AI: A Computational Perspectivecited by 93
  4. 2021Bias in Machine Learning Software: Why? How? What to do?cited by 92
  5. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  6. 2022Synthetic Data -- what, why and how?cited by 66
  7. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  8. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  9. 2021Agent Incentives: A Causal Perspectivecited by 51
  10. 2022Causal Conceptions of Fairness and their Consequencescited by 38
  11. 2022Marrying Fairness and Explainability in Supervised Learningcited by 23
  12. 2024Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumventioncited by 21
38 more
  1. 2022Counterfactual Fairness with Partially Known Causal Graphcited by 20
  2. 2021FairMask: Better Fairness via Model-based Rebalancing of Protected Attributescited by 19
  3. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  4. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  5. 2022D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Biascited by 18
  6. 2023Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencodercited by 17
  7. 2022Causal Discovery for Fairnesscited by 16
  8. 2021Achieving Counterfactual Fairness for Causal Banditcited by 15
  9. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  10. 2021Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classificationcited by 13
  11. 2022Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairnesscited by 13
  12. 2021From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigationcited by 11
  13. 2021Fairness-Aware Unsupervised Feature Selectioncited by 10
  14. 2021Attributing Fair Decisions with Attention Interventionscited by 10
  15. 2021Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice modelscited by 10
  16. 2022Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairnesscited by 10
  17. 2022Attainability and Optimality: The Equalized Odds Fairness Revisitedcited by 10
  18. 2023Causal Fairness under Unobserved Confounding: A Neural Sensitivity Frameworkcited by 10
  19. 2024AIM: Attributing, Interpreting, Mitigating Data Unfairnesscited by 9
  20. 2022Disentangled Representation with Causal Constraints for Counterfactual Fairnesscited by 7
  21. 2023Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factorscited by 7
  22. 2024Fairness Evaluation with Item Response Theorycited by 7
  23. 2021End-To-End Bias Mitigation: Removing Gender Bias in Deep Learningcited by 6
  24. 2022On Learning and Testing of Counterfactual Fairness through Data Preprocessingcited by 6
  25. 2024Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approachcited by 6
  26. 2024Local Causal Discovery for Structural Evidence of Direct Discriminationcited by 6
  27. 2022Social Bias Meets Data Bias: The Impacts of Labeling and Measurement Errors on Fairness Criteriacited by 5
  28. 2024What is Fair? Defining Fairness in Machine Learning for Healthcited by 5
  29. 2021Fair-SSL: Building fair ML Software with less datacited by 4
  30. 2021Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairnesscited by 3
  31. 2022The Fairness Field Guide: Perspectives from Social and Formal Sciencescited by 3
  32. 2022Causal Fairness Assessment of Treatment Allocation with Electronic Health Recordscited by 3
  33. 2023Procedural Fairness Through Decoupling Objectionable Data Generating Componentscited by 3
  34. 2024What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learningcited by 3
  35. 2022Distraction is All You Need for Fairnesscited by 2
  36. 2022SCALES: From Fairness Principles to Constrained Decision-Makingcited by 2
  37. 2023Designing Equitable Algorithmscited by 2
  38. 2024Formalising Anti-Discrimination Law in Automated Decision Systemscited by 2

50 most cited of 71 All 71 (JSON)