mlsanityData to 7 Oct 2026

Two Simple Ways to Learn Individual Fairness Metrics from Data

arXiv 2006.11439 ↗First posted 19 Jun 2020stat.ML cs.LG stat.MEcited by 54

Not on the map. Why?

Abstract (arXiv)

Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific fair metric that encodes our intuition of what is fair and unfair for the ML task at hand, and the lack of a widely accepted fair metric for many ML tasks is the main barrier to broader adoption of individual fairness. In this paper, we present two simple ways to learn fair metrics from a variety of data types. We show empirically that fair training with the learned metrics leads to improved fairness on three machine learning tasks susceptible to gender and racial biases. We also provide theoretical guarantees on the statistical performance of both approaches.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 14; 2023: 16; 2024: 8; 2025: 6; 2026: 3.

54 papers.

Sort:

  1. 2021Post-processing for Individual Fairnesscited by 61
  2. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  3. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  4. 2022Learning fair representation with a parametric integral probability metriccited by 20
  5. 2021Latent Space Smoothing for Individually Fair Representationscited by 18
  6. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  7. 2021Unified Group Fairness on Federated Learningcited by 15
  8. 2023Uncertainty-based Fairness Measurescited by 15
  9. 2021Statistical inference for individual fairnesscited by 13
  10. 2022Domain Adaptation meets Individual Fairness. And they get alongcited by 13
  11. 2021Individually Fair Gradient Boostingcited by 12
  12. 2023Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approachcited by 12
38 more
  1. 2023Individual Fairness under Uncertaintycited by 11
  2. 2024Rethinking Fair Graph Neural Networks from Re-balancingcited by 11
  3. 2024AIM: Attributing, Interpreting, Mitigating Data Unfairnesscited by 9
  4. 2022Multi-disciplinary fairness considerations in machine learning for clinical trialscited by 8
  5. 2022Learning Antidote Data to Individual Unfairnesscited by 8
  6. 2021Individually Fair Rankingcited by 7
  7. 2023Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairnesscited by 7
  8. 2025Fair Deepfake Detectors Can Generalizecited by 7
  9. 2022Private and Reliable Neural Network Inferencecited by 6
  10. 2023GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hintcited by 6
  11. 2022Individually Fair Learning with One-Sided Feedbackcited by 5
  12. 2022iFlipper: Label Flipping for Individual Fairnesscited by 5
  13. 2022Human-Guided Fair Classification for Natural Language Processingcited by 5
  14. 2024What is Fair? Defining Fairness in Machine Learning for Healthcited by 5
  15. 2022Manifestations of Xenophobia in AI Systemscited by 4
  16. 2023Retiring DeltaDP: New Distribution-Level Metrics for Demographic Paritycited by 4
  17. 2025Rethinking Individual Fairness in Deepfake Detectioncited by 4
  18. 2022SLIDE: a surrogate fairness constraint to ensure fairness consistencycited by 3
  19. 2023Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustnesscited by 3
  20. 2024Monotone Individual Fairnesscited by 3
  21. 2024FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Predictioncited by 3
  22. 2023Achieving Counterfactual Fairness with Imperfect Structural Causal Modelcited by 2
  23. 2023To be Robust and to be Fair: Aligning Fairness with Robustnesscited by 2
  24. 2023Certification of Distributional Individual Fairnesscited by 2
  25. 2024Positive-Sum Fairness: Leveraging Demographic Attributes to Achieve Fair AI Outcomes Without Sacrificing Group Gainscited by 2
  26. 2022fAux: Testing Individual Fairness via Gradient Alignmentcited by 1
  27. 2023Software Doping Analysis for Human Oversightcited by 1
  28. 2023A Canonical Data Transformation for Achieving Inter- and Within-group Fairnesscited by 1
  29. 2023Identifying Reasons for Bias: An Argumentation-Based Approachcited by 1
  30. 2026Investigating Bias and Fairness in Appearance-based Gaze Estimationcited by 1
  31. 2022Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributionscited by 0
  32. 2023Counterpart Fairness -- Addressing Systematic between-group Differences in Fairness Evaluationcited by 0
  33. 2023The Flawed Foundations of Fair Machine Learningcited by 0
  34. 2023Democratize with Care: The need for fairness specific features in user-interface based open source AutoML toolscited by 0
  35. 2024On the Impact of Output Perturbation on Fairness in Binary Linear Classificationcited by 0
  36. 2024Individual Fairness Through Reweighting and Tuningcited by 0
  37. 2025Testing Individual Fairness in Graph Neural Networkscited by 0
  38. 2025SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encodingcited by 0

50 most cited of 54 All 54 (JSON)