一句话：提出 FairHOME，用输入高阶变异体集成在推理阶段提升 ML 软件的交叉公平性。
交叉公平性要求机器学习软件在由多个受保护属性定义的子群上均表现公平。本文提出 FairHOME，一种受社会科学多样性理论启发的输入高阶变异集成方法，用于在推理阶段提升交叉公平性。FairHOME 为每个输入实例生成代表不同子群的变异体，从而拓展决策视角；与组合不同模型预测的传统集成不同，它组合同一 ML 模型对原始输入及其变异体的预测来做出最终决策，且无需重新训练模型，因此也适用于已部署软件。作者在 24 个决策任务上使用常用指标，将 FairHOME 与 7 种先进公平性提升方法对比。结果表明 FairHOME 在所有指标上持续更优，平均将交叉公平性提升 47.5%，比当前最佳方法高 9.6 个百分点。
Intersectional fairness is a critical requirement for Machine Learning (ML) software, demanding fairness across subgroups defined by multiple protected attributes. This paper introduces FairHOME, a novel ensemble approach using higher order mutation of inputs to enhance intersectional fairness of ML software during the inference phase. Inspired by social science theories highlighting the benefits of diversity, FairHOME generates mutants representing diverse subgroups for each input instance, thus broadening the array of perspectives to foster a fairer decision-making process. Unlike conventional ensemble methods that combine predictions made by different models, FairHOME combines predictions for the original input and its mutants, all generated by the same ML model, to reach a final decision. Notably, FairHOME is even applicable to deployed ML software as it bypasses the need for training new models. We extensively evaluate FairHOME against seven state-of-the-art fairness improvement methods across 24 decision-making tasks using widely adopted metrics. FairHOME consistently outperforms existing methods across all metrics considered. On average, it enhances intersectional fairness by 47.5 %, surpassing the currently best-performing method by 9.6 percentage points.
DOI 原文 ·
@inproceedings{paperbot8684,
title = {Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software},
author = {Zhenpeng Chen and Xinyue Li and Jie M. Zhang and Federica Sarro and Yang Liu},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00122}
}