mlsanityData to 7 Oct 2026

An Intersectional Definition of Fairness

arXiv 1807.08362 ↗First posted 22 Jul 2018cs.LG cs.CY stat.MLcited by 126

Not on the map. Why?

Abstract (arXiv)

We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our intersectional fairness criteria. Case studies on census data and the COMPAS criminal recidivism dataset demonstrate the utility of our methods.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 28; 2023: 28; 2024: 20; 2025: 22; 2026: 10.

126 papers.

Sort:

By area:

  1. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  2. 2022A Systematic Study of Bias Amplificationcited by 65
  3. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  4. 2021Directional Bias Amplificationcited by 54
  5. 2021Characterizing Intersectional Group Fairness with Worst-Case Comparisonscited by 42
  6. 2023A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challengescited by 41
  7. 2023Improving Fairness in Deepfake Detectioncited by 40
  8. 2023Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairnesscited by 26
  9. 2022Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approachescited by 23
  10. 2021When Fair Ranking Meets Uncertain Inferencecited by 22
  11. 2022Fairness Amidst Non-IID Graph Data: A Literature Reviewcited by 20
  12. 2021OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learningcited by 18
38 more
  1. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  2. 2024A Unified Debiasing Approach for Vision-Language Models across Modalities and Taskscited by 18
  3. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  4. 2021InfoFair: Information-Theoretic Intersectional Fairnesscited by 15
  5. 2023Multi-dimensional discrimination in Law and Machine Learning -- A comparative overviewcited by 15
  6. 2022Distributionally Robust Survival Analysis: A Novel Fairness Loss Without Demographicscited by 14
  7. 2024Verifiable evaluations of machine learning models using zkSNARKscited by 14
  8. 2021Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classificationcited by 13
  9. 2024The Pursuit of Fairness in Artificial Intelligence Models: A Surveycited by 13
  10. 2024Fairness in Survival Analysis with Distributionally Robust Optimizationcited by 13
  11. 2022Bounding and Approximating Intersectional Fairness through Marginal Fairnesscited by 11
  12. 2021Interpretable and Fair Boolean Rule Sets via Column Generationcited by 10
  13. 2023Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equitycited by 9
  14. 2022Fair admission risk prediction with proportional multicalibrationcited by 8
  15. 2023Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Predictioncited by 8
  16. 2023Designing Long-term Group Fair Policies in Dynamical Systemscited by 8
  17. 2024A structured regression approach for evaluating model performance across intersectional subgroupscited by 8
  18. 2024Intersectional Two-sided Fairness in Recommendationcited by 8
  19. 2022Fairness Implications of Encoding Protected Categorical Attributescited by 7
  20. 2025Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMscited by 7
  21. 2021Identifying Biased Subgroups in Ranking and Classificationcited by 6
  22. 2023Optimizing fairness tradeoffs in machine learning with multiobjective meta-modelscited by 6
  23. 2021Disaggregated Interventions to Reduce Inequalitycited by 5
  24. 2024Towards Standardizing AI Bias Explorationcited by 5
  25. 2024EARN Fairness: Explaining, Asking, Reviewing, and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholderscited by 5
  26. 2024The Intersectionality Problem for Algorithmic Fairnesscited by 5
  27. 2021Multi-fairness under class-imbalancecited by 4
  28. 2021Improving Fairness of AI Systems with Lossless De-biasingcited by 4
  29. 2021User Acceptance of Gender Stereotypes in Automated Career Recommendationscited by 4
  30. 2022Fairness in Forecasting of Observations of Linear Dynamical Systemscited by 4
  31. 2023Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and financecited by 4
  32. 2023How to address monotonicity for model risk management?cited by 4
  33. 2022The Fairness Field Guide: Perspectives from Social and Formal Sciencescited by 3
  34. 2022Fairness-Aware Naive Bayes Classifier for Data with Multiple Sensitive Featurescited by 3
  35. 2022Debiasing Word Embeddings with Nonlinear Geometrycited by 3
  36. 2022Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributescited by 3
  37. 2023Equal Confusion Fairness: Measuring Group-Based Disparities in Automated Decision Systemscited by 3
  38. 2023The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languagescited by 3

50 most cited of 126 All 126 (JSON)