Adversarial Reweighting Guided by Wasserstein Distance for Bias Mitigation

TL;DR

This paper introduces an adversarial reweighting technique guided by Wasserstein distance to mitigate representation bias in machine learning, effectively balancing data distribution and reducing discrimination without harming accuracy.

Contribution

It proposes a novel adversarial reweighting method that emphasizes samples near minority groups, addressing under-representation bias more effectively than existing approaches.

Findings

Reduces bias while maintaining classification accuracy

Outperforms state-of-the-art bias mitigation methods

Effective on both image and tabular datasets

Abstract

The unequal representation of different groups in a sample population can lead to discrimination of minority groups when machine learning models make automated decisions. To address these issues, fairness-aware machine learning jointly optimizes two (or more) metrics aiming at predictive effectiveness and low unfairness. However, the inherent under-representation of minorities in the data makes the disparate treatment of subpopulations less noticeable and difficult to deal with during learning. In this paper, we propose a novel adversarial reweighting method to address such \emph{representation bias}. To balance the data distribution between the majority and the minority groups, our approach deemphasizes samples from the majority group. To minimize empirical risk, our method prefers samples from the majority group that are close to the minority group as evaluated by the Wasserstein distance. Our theoretical analysis shows the effectiveness of our adversarial reweighting approach. Experiments demonstrate that our approach mitigates bias without sacrificing classification accuracy, outperforming related state-of-the-art methods on image and tabular benchmark datasets.