mlsanityData to 7 Oct 2026

Fairness with Continuous Optimal Transport

arXiv 2101.02084 ↗First posted 6 Jan 2021cs.LG stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

Whilst optimal transport (OT) is increasingly being recognized as a powerful and flexible approach for dealing with fairness issues, current OT fairness methods are confined to the use of discrete OT. In this paper, we leverage recent advances from the OT literature to introduce a stochastic-gradient fairness method based on a dual formulation of continuous OT. We show that this method gives superior performance to discrete OT methods when little data is available to solve the OT problem, and similar performance otherwise. We also show that both continuous and discrete OT methods are able to continually adjust the model parameters to adapt to different levels of unfairness that might occur in real-world applications of ML systems.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 6 Jan 2021.

Builds on

23 of 43 references.

References · 23

  1. 2018Computational Optimal Transportcited by 765
  2. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  3. 2020Fairness in Machine Learningcited by 194
  4. 2016Stochastic Optimization for Large-scale Optimal Transportcited by 188
  5. 2018Delayed Impact of Fair Machine Learningcited by 183
  6. 2016Fairness in Learning: Classic and Contextual Banditscited by 167
  7. 2019Wasserstein Fair Classificationcited by 131
  8. 2017Large-Scale Optimal Transport and Mapping Estimationcited by 120
  9. 2020Fair Regression with Wasserstein Barycenterscited by 99
  10. 2016Fairness in Reinforcement Learningcited by 93
  11. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  12. 2017On Formalizing Fairness in Prediction with Machine Learningcited by 65
11 more
  1. 2018Online Learning with an Unknown Fairness Metriccited by 61
  2. 2019Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributionscited by 48
  3. 2019Causal Modeling for Fairness in Dynamical Systemscited by 46
  4. 2020Fairness in Learning-Based Sequential Decision Algorithms: A Surveycited by 35
  5. 2020Ensuring Fairness Beyond the Training Datacited by 35
  6. 2019Improved Adversarial Learning for Fair Classificationcited by 25
  7. 2020Review of Mathematical frameworks for Fairness in Machine Learningcited by 21
  8. 2018On preserving non-discrimination when combining expert advicecited by 12
  9. 2020Projection to Fairness in Statistical Learningcited by 3
  10. 2019Consequential Ranking Algorithms and Long-term Welfarecited by 2
  11. 2019Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP Inferencecited by 1

Built on by

Cited by year

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

9 papers.

  1. 2022Fair learning with Wasserstein barycenters for non-decomposable performance measurescited by 24
  2. 2022An improved central limit theorem and fast convergence rates for entropic transportation costscited by 18
  3. 2022Learning Counterfactually Invariant Predictorscited by 10
  4. 2022Obtaining Dyadic Fairness by Optimal Transportcited by 6
  5. 2021Everything is Relative: Understanding Fairness with Optimal Transportcited by 2
  6. 2022fAux: Testing Individual Fairness via Gradient Alignmentcited by 1
  7. 2023Adversarial Reweighting Guided by Wasserstein Distance for Bias Mitigationcited by 1
  8. 2024Auditing and Enforcing Conditional Fairness via Optimal Transportcited by 1
  9. 2025Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regressioncited by 1