Fairness with Continuous Optimal Transport
arXiv:2101.02084
Abstract
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.
References in corpus (12)
- Scikit-learn: Machine Learning in Python
- Fairness in Machine Learning
- On Formalizing Fairness in Prediction with Machine Learning
- Training individually fair ML models with Sensitive Subspace Robustness
- Obtaining fairness using optimal transport theory
- Improved Adversarial Learning for Fair Classification
- Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions
- Wasserstein Fair Classification
- Review of Mathematical frameworks for Fairness in Machine Learning
- Fair Regression with Wasserstein Barycenters
- On preserving non-discrimination when combining expert advice
- Consequential Ranking Algorithms and Long-term Welfare