mlsanityData to 14 Oct 2026

Testing Group Fairness via Optimal Transport Projections

arXiv 2106.01070 ↗First posted 2 Jun 2021stat.ML cs.CY cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions. The proposed test is a flexible, interpretable, and statistically rigorous tool for auditing whether exhibited biases are intrinsic to the algorithm or due to the randomness in the data. The statistical challenges, which may arise from multiple impact criteria that define group fairness and which are discontinuous on model parameters, are conveniently tackled by projecting the empirical measure onto the set of group-fair probability models using optimal transport. This statistic is efficiently computed using linear programming and its asymptotic distribution is explicitly obtained. The proposed framework can also be used to test for testing composite fairness hypotheses and fairness with multiple sensitive attributes. The optimal transport testing formulation improves interpretability by characterizing the minimal covariate perturbations that eliminate the bias observed in the audit.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

18 of 43 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. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  4. 2017On Fairness and Calibrationcited by 406
  5. 2017Algorithmic decision making and the cost of fairnesscited by 403
  6. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  7. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  8. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  9. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 151
  10. 2018Aequitas: A Bias and Fairness Audit Toolkitcited by 147
  11. 2020Algorithmic Fairnesscited by 143
  12. 2019FlipTest: Fairness Testing via Optimal Transportcited by 51
6 more
  1. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  2. 2020A Statistical Test for Probabilistic Fairnesscited by 25
  3. 2020Auditing ML Models for Individual Bias and Unfairnesscited by 18
  4. 2018Confidence Intervals for Testing Disparate Impact in Fair Learningcited by 9
  5. 2019Distributionally Robust Formulation and Model Selection for the Graphical Lassocited by 7
  6. 2015FairTest: Discovering Unwarranted Associations in Data-Driven Applicationscited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 10; 2024: 5; 2025: 4.

23 papers.

Sort:

  1. 2023Recent Advances in Optimal Transport for Machine Learningcited by 66
  2. 2021Statistical Analysis of Wasserstein Distributionally Robust Estimatorscited by 27
  3. 2023Auditing Fairness by Bettingcited by 25
  4. 2023Statistical Inference for Fairness Auditingcited by 20
  5. 2022Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metricscited by 18
  6. 2022Optimal Transport of Classifiers to Fairnesscited by 12
  7. 2024PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attackscited by 11
  8. 2023Scalable Unbalanced Sobolev Transport for Measures on a Graphcited by 10
  9. 2022Distributionally Robust Fair Principal Components via Geodesic Descentscited by 9
  10. 2024OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transportcited by 8
  11. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  12. 2023Optimal Transport for Measures with Noisy Tree Metriccited by 7
11 more
  1. 2025Robust ML Auditing using Prior Knowledgecited by 6
  2. 2023Group-blind optimal transport to group parity and its constrained variantscited by 4
  3. 2023Mitigating Source Bias for Fairer Weak Supervisioncited by 3
  4. 2023FairRec: Fairness Testing for Deep Recommender Systemscited by 3
  5. 2024Stability Evaluation via Distributional Perturbation Analysiscited by 1
  6. 2024Auditing and Enforcing Conditional Fairness via Optimal Transportcited by 1
  7. 2023RobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient Searchcited by 0
  8. 2024Peer-induced Fairness: A Causal Approach for Algorithmic Fairness Auditingcited by 0
  9. 2025From Fragile to Certified: Wasserstein Audits of Group Fairness Under Distribution Shiftcited by 0
  10. 2025Cost Efficient Fairness Audit Under Partial Feedbackcited by 0
  11. 2025Wasserstein projection distance for fairness testing of regression modelscited by 0