mlsanityData to 14 Oct 2026

Algorithmic Fairness: Not a Purely Technical but Socio-Technical Property

arXiv 2506.12556 ↗First posted 14 Jun 2025cs.LG cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

The rapid trend of deploying artificial intelligence (AI) and machine learning (ML) systems in socially consequential domains has raised growing concerns about their trustworthiness, including potential discriminatory behaviours. Research in algorithmic fairness has generated a proliferation of mathematical definitions and metrics, yet persistent misconceptions and limitations -- both within and beyond the fairness community -- limit their effectiveness, such as an unreached consensus on its understanding, prevailing measures primarily tailored to binary group settings, and superficial handling for intersectional contexts. Here we critically remark on these misconceptions and argue that fairness cannot be reduced to purely technical constraints on models; we also examine the limitations of existing fairness measures through conceptual analysis and empirical illustrations, showing their limited applicability in the face of complex real-world scenarios, challenging prevailing views on the incompatibility between accuracy and fairness as well as that among fairness measures themselves, and outlining three worth-considering principles in the design of fairness measures. We believe these findings will help bridge the gap between technical formalisation and social realities and meet the challenges of real-world AI/ML deployment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 64 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

35 of 64 references.

References · 35

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2017Counterfactual Fairnesscited by 804
  4. 2014Certifying and removing disparate impactcited by 715
  5. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  6. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  7. 2017On Fairness and Calibrationcited by 406
  8. 2017Algorithmic decision making and the cost of fairnesscited by 403
  9. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  10. 2020Fairness in Machine Learning: A Surveycited by 370
  11. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  12. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
23 more
  1. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 222
  2. 2017Avoiding Discrimination through Causal Reasoningcited by 194
  3. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  4. 2017Fairness in Machine Learning: Lessons from Political Philosophycited by 149
  5. 2017Fair Inference On Outcomescited by 144
  6. 2019Wasserstein Fair Classificationcited by 131
  7. 2018An Intersectional Definition of Fairnesscited by 127
  8. 2023Generative Language Models Exhibit Social Identity Biasescited by 111
  9. 2018A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indicescited by 97
  10. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 85
  11. 2018An Empirical Study of Rich Subgroup Fairness for Machine Learningcited by 81
  12. 2017On Formalizing Fairness in Prediction with Machine Learningcited by 65
  13. 2015On the relation between accuracy and fairness in binary classificationcited by 48
  14. 2019AdaFair: Cumulative Fairness Adaptive Boostingcited by 45
  15. 2021Characterizing Intersectional Group Fairness with Worst-Case Comparisonscited by 42
  16. 2023A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challengescited by 41
  17. 2022FairGBM: Gradient Boosting with Fairness Constraintscited by 25
  18. 2024Procedural Fairness in Machine Learningcited by 4
  19. 2024Minimax Group Fairness in Strategic Classificationcited by 4
  20. 2023Improving Fairness with Ensemble Combination: Margin-Dependent Boundscited by 3
  21. 2024Measuring Model-Induced Discrimination via Efficient Fairness Approximationcited by 2
  22. 2025Joint Evaluation of Fairness and Relevance in Recommender Systems with Pareto Frontiercited by 2
  23. 2024Approximating Discrimination Within Models When Faced With Several Non-Binary Sensitive Attributescited by 1

Built on by

Not cited yet.