Everything is Relative: Understanding Fairness with Optimal Transport

Abstract

To study discrimination in automated decision-making systems, scholars have proposed several definitions of fairness, each expressing a different fair ideal. These definitions require practitioners to make complex decisions regarding which notion to employ and are often difficult to use in practice since they make a binary judgement a system is fair or unfair instead of explaining the structure of the detected unfairness. We present an optimal transport-based approach to fairness that offers an interpretable and quantifiable exploration of bias and its structure by comparing a pair of outcomes to one another. In this work, we use the optimal transport map to examine individual, subgroup, and group fairness. Our framework is able to recover well known examples of algorithmic discrimination, detect unfairness when other metrics fail, and explore recourse opportunities.

References in corpus (10)

• The Measure and Mismeasure of Fairness
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Towards a Critical Race Methodology in Algorithmic Fairness
• On the (im)possibility of fairness
• The Frontiers of Fairness in Machine Learning
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Equalizing Recourse across Groups
• Auditing ML Models for Individual Bias and Unfairness
• Fairness with Continuous Optimal Transport