mlsanityData to 14 Oct 2026

Equalised Odds is not Equal Individual Odds: Post-processing for Group and Individual Fairness

arXiv 2304.09779 ↗First posted 19 Apr 2023cs.LG cs.CY math.OCcited by 4

Not on the map. Why?

Abstract (arXiv)

Group fairness is achieved by equalising prediction distributions between protected sub-populations; individual fairness requires treating similar individuals alike. These two objectives, however, are incompatible when a scoring model is calibrated through discontinuous probability functions, where individuals can be randomly assigned an outcome determined by a fixed probability. This procedure may provide two similar individuals from the same protected group with classification odds that are disparately different -- a clear violation of individual fairness. Assigning unique odds to each protected sub-population may also prevent members of one sub-population from ever receiving equal chances of a positive outcome to another, which we argue is another type of unfairness called individual odds. We reconcile all this by constructing continuous probability functions between group thresholds that are constrained by their Lipschitz constant. Our solution preserves the model's predictive power, individual fairness and robustness while ensuring group fairness.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 18 of its 51 references that are in the map. First posted on arXiv 19 Apr 2023.

Builds on

18 of 51 references.

References · 18

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2018A Reductions Approach to Fair Classificationcited by 587
  4. 2018Why Is My Classifier Discriminatory?cited by 143
  5. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  6. 2019On the Apparent Conflict Between Individual and Group Fairnesscited by 126
  7. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  8. 2020Model Interpretability through the Lens of Computational Complexitycited by 75
  9. 2018Bias Mitigation Post-processing for Individual and Group Fairnesscited by 72
  10. 2021Post-processing for Individual Fairnesscited by 61
  11. 2018The age of secrecy and unfairness in recidivism predictioncited by 53
  12. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 51
6 more
  1. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  2. 2019Equalized odds postprocessing under imperfect group informationcited by 48
  3. 2020Achieving Equalized Odds by Resampling Sensitive Attributescited by 42
  4. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  5. 2022Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiencycited by 19
  6. 2022Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicitycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Perturbation Effects on Robustness and Individual Fairnesscited by 0
  2. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  3. 2026Trade-offs Between Individual and Group Fairness in Machine Learning: A Comprehensive Reviewcited by 0
  4. 2026Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systemscited by 0