mlsanityData to 7 Oct 2026

Revisiting Technical Bias Mitigation Strategies

arXiv 2410.17433 ↗First posted 22 Oct 2024cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Efforts to mitigate bias and enhance fairness in the artificial intelligence (AI) community have predominantly focused on technical solutions. While numerous reviews have addressed bias in AI, this review uniquely focuses on the practical limitations of technical solutions in healthcare settings, providing a structured analysis across five key dimensions affecting their real-world implementation: who defines bias and fairness; which mitigation strategy to use and prioritize among dozens that are inconsistent and incompatible; when in the AI development stages the solutions are most effective; for which populations; and the context in which the solutions are designed. We illustrate each limitation with empirical studies focusing on healthcare and biomedical applications. Moreover, we discuss how value-sensitive AI, a framework derived from technology design, can engage stakeholders and ensure that their values are embodied in bias and fairness mitigation solutions. Finally, we discuss areas that require further investigation and provide practical recommendations to address the limitations covered in the study.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 133 references that are in the map. First posted on arXiv 22 Oct 2024.

Builds on

39 of 133 references.

References · 39

  1. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  4. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  5. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
  6. 2020Fairness in Machine Learning: A Surveycited by 369
  7. 2020A Brief Review of Domain Adaptationcited by 287
  8. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  9. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
  10. 2021The Values Encoded in Machine Learning Researchcited by 172
  11. 2022Power to the People? Opportunities and Challenges for Participatory AIcited by 137
  12. 2018An Intersectional Definition of Fairnesscited by 126
27 more
  1. 2019On the Apparent Conflict Between Individual and Group Fairnesscited by 126
  2. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  3. 2023Generative AIcited by 119
  4. 2020Ethical Machine Learning in Health Carecited by 112
  5. 2023The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practicecited by 86
  6. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 83
  7. 2020Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AIcited by 81
  8. 2017On Formalizing Fairness in Prediction with Machine Learningcited by 65
  9. 2022Algorithmic Fairness Datasets: the Story so Farcited by 51
  10. 2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settingscited by 45
  11. 2019Transfer of Machine Learning Fairness across Domainscited by 36
  12. 2020Adapting a Kidney Exchange Algorithm to Align with Human Valuescited by 36
  13. 2019The Sensitivity of Counterfactual Fairness to Unmeasured Confoundingcited by 35
  14. 2022A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifierscited by 30
  15. 2021Soliciting Stakeholders' Fairness Notions in Child Maltreatment Predictive Systemscited by 27
  16. 2021Fairness Perceptions of Algorithmic Decision-Making: A Systematic Review of the Empirical Literaturecited by 27
  17. 2017Calibration for the (Computationally-Identifiable) Massescited by 23
  18. 2022D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Biascited by 18
  19. 2019Fairness and Missing Valuescited by 16
  20. 2022Domain Adaptation meets Individual Fairness. And they get alongcited by 13
  21. 2022Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairnesscited by 13
  22. 2024The Pursuit of Fairness in Artificial Intelligence Models: A Surveycited by 13
  23. 2023An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literaturecited by 8
  24. 2023Maximal Fairnesscited by 6
  25. 2024The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africacited by 5
  26. 2020One-vs.-One Mitigation of Intersectional Bias: A General Method to Extend Fairness-Aware Binary Classificationcited by 3
  27. 2024Towards Clinical AI Fairness: Filling Gaps in the Puzzlecited by 1

Built on by

Not cited yet.