mlsanityData to 14 Oct 2026

On Formalizing Fairness in Prediction with Machine Learning

arXiv 1710.03184 ↗First posted 9 Oct 2017cs.LG cs.AI stat.MLcited by 65

Not on the map. Why?

Abstract (arXiv)

Machine learning algorithms for prediction are increasingly being used in critical decisions affecting human lives. Various fairness formalizations, with no firm consensus yet, are employed to prevent such algorithms from systematically discriminating against people based on certain attributes protected by law. The aim of this article is to survey how fairness is formalized in the machine learning literature for the task of prediction and present these formalizations with their corresponding notions of distributive justice from the social sciences literature. We provide theoretical as well as empirical critiques of these notions from the social sciences literature and explain how these critiques limit the suitability of the corresponding fairness formalizations to certain domains. We also suggest two notions of distributive justice which address some of these critiques and discuss avenues for prospective fairness formalizations.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 17; 2024: 10; 2025: 8; 2026: 2.

65 papers.

Sort:

By area:

  1. 2021Strong Optimal Classification Treescited by 28
  2. 2021Fairness Perceptions of Algorithmic Decision-Making: A Systematic Review of the Empirical Literaturecited by 27
  3. 2021UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Modelscited by 23
  4. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  5. 2023Improving Recommendation Fairness via Data Augmentationcited by 18
  6. 2021Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AIcited by 16
  7. 2022FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modificationcited by 15
  8. 2022Counterfactual Fairness Is Basically Demographic Paritycited by 15
  9. 2022Survey on Fair Reinforcement Learning: Theory and Practicecited by 14
  10. 2024Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agentscited by 14
  11. 2021Personalized Education in the AI Era: What to Expect Next?cited by 13
  12. 2021Towards Equity and Algorithmic Fairness in Student Grade Predictioncited by 13
38 more
  1. 2022The Long Arc of Fairness: Formalisations and Ethical Discoursecited by 13
  2. 2021A Unified Approach to Fair Online Learning via Blackwell Approachabilitycited by 12
  3. 2023FairGen: Towards Fair Graph Generationcited by 12
  4. 2023Evaluating the Fairness of Discriminative Foundation Models in Computer Visioncited by 12
  5. 2021Fairness with Continuous Optimal Transportcited by 10
  6. 2021Distributive Justice and Fairness Metrics in Automated Decision-making: How Much Overlap Is There?cited by 10
  7. 2021Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice modelscited by 10
  8. 2022Survey on Fairness Notions and Related Tensionscited by 9
  9. 2022Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraintscited by 9
  10. 2023Fairness-enhancing deep learning for ride-hailing demand predictioncited by 9
  11. 2024Properties of fairness measures in the context of varying class imbalance and protected group ratioscited by 7
  12. 2021End-To-End Bias Mitigation: Removing Gender Bias in Deep Learningcited by 6
  13. 2022What Is Fairness? On the Role of Protected Attributes and Fictitious Worldscited by 6
  14. 2023DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisioncited by 6
  15. 2022FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guaranteecited by 5
  16. 2023Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithmscited by 5
  17. 2021User Acceptance of Gender Stereotypes in Automated Career Recommendationscited by 4
  18. 2021Statistical discrimination in learning agentscited by 4
  19. 2022Fairness in Forecasting of Observations of Linear Dynamical Systemscited by 4
  20. 2022The Fairness Field Guide: Perspectives from Social and Formal Sciencescited by 3
  21. 2023Improving Fairness with Ensemble Combination: Margin-Dependent Boundscited by 3
  22. 2022Mitigating Algorithmic Bias with Limited Annotationscited by 2
  23. 2022Diversely Regularized Matrix Factorization for Accurate and Aggregately Diversified Recommendationcited by 2
  24. 2023Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluationcited by 2
  25. 2023FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithmscited by 2
  26. 2023Automated discovery of trade-off between utility, privacy and fairness in machine learning modelscited by 2
  27. 2024Measuring Model-Induced Discrimination via Efficient Fairness Approximationcited by 2
  28. 2025Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyondcited by 2
  29. 2025Controllable Feature Whitening for Hyperparameter-Free Bias Mitigationcited by 2
  30. 2022fAux: Testing Individual Fairness via Gradient Alignmentcited by 1
  31. 2022Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Datacited by 1
  32. 2023Matrix Estimation for Individual Fairnesscited by 1
  33. 2023Provable Detection of Propagating Sampling Bias in Prediction Modelscited by 1
  34. 2023Robust probabilistic inference via a constrained transport metriccited by 1
  35. 2023Towards Fair and Explainable AI using a Human-Centered AI Approachcited by 1
  36. 2023A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classificationcited by 1
  37. 2024Data Ethics in the Era of Healthcare Artificial Intelligence in Africa: An Ubuntu Philosophy Perspectivecited by 1
  38. 2024Approximating Discrimination Within Models When Faced With Several Non-Binary Sensitive Attributescited by 1

50 most cited of 65 All 65 (JSON)