Multi-fairness under class-imbalance

TL;DR

This paper introduces a new fairness measure called Multi-Max Mistreatment (MMM) to address bias in multi-attribute, class-imbalanced datasets, proposing a boosting method that improves fairness and accuracy for minority groups.

Contribution

It proposes MMM, a novel fairness metric that considers multi-attribute protected groups and class membership, along with a boosting approach to mitigate bias in imbalanced datasets.

Findings

Outperforms state-of-the-art methods in balanced group and class performance

Achieves higher accuracy for protected minority groups

Effectively reduces discrimination in multi-attribute, imbalanced datasets

Abstract

Recent studies showed that datasets used in fairness-aware machine learning for multiple protected attributes (referred to as multi-discrimination hereafter) are often imbalanced. The class-imbalance problem is more severe for the often underrepresented protected group (e.g. female, non-white, etc.) in the critical minority class. Still, existing methods focus only on the overall error-discrimination trade-off, ignoring the imbalance problem, thus amplifying the prevalent bias in the minority classes. Therefore, solutions are needed to solve the combined problem of multi-discrimination and class-imbalance. To this end, we introduce a new fairness measure, Multi-Max Mistreatment (MMM), which considers both (multi-attribute) protected group and class membership of instances to measure discrimination. To solve the combined problem, we propose a boosting approach that incorporates MMM-costs in the distribution update and post-training selects the optimal trade-off among accurate, balanced, and fair solutions. The experimental results show the superiority of our approach against state-of-the-art methods in producing the best balanced performance across groups and classes and the best accuracy for the protected groups in the minority class.