一句话：提出 MAAT 集成方法，通过组合公平性与性能两个不同目标的模型，显著改善 ML 软件的公平性-性能权衡。
机器学习软件可能因公平性缺陷做出不公平决策，而修复公平性缺陷常会引入性能缺陷，因此公平性-性能权衡成为重要问题。本文提出 MAAT，一种新型集成方法。与传统集成方法组合同一学习目标的模型不同，MAAT 组合分别针对公平性和机器学习性能优化的模型。作者在 5 种最新方法、9 个软件决策任务和 15 种公平性-性能度量上进行了广泛评估。结果表明，MAAT 显著优于现有技术：在 92.2% 的总体评估案例中击败了近期基准工具构建的权衡基线，比当前最佳技术高 12.2 个百分点；并且其优势在所研究的所有任务和度量上均成立。代码和数据已公开。
Machine Learning (ML) software can lead to unfair and unethical decisions, making software fairness bugs an increasingly significant concern for software engineers. However, addressing fairness bugs often comes at the cost of introducing more ML performance (e.g., accuracy) bugs. In this paper, we propose MAAT, a novel ensemble approach to improving fairness-performance trade-off for ML software. Conventional ensemble methods combine different models with identical learning objectives. MAAT, instead, combines models optimized for different objectives: fairness and ML performance. We conduct an extensive evaluation of MAAT with 5 state-of-the-art methods, 9 software decision tasks, and 15 fairness-performance measurements. The results show that MAAT significantly outperforms the state-of-the-art. In particular, MAAT beats the trade-off baseline constructed by a recent benchmarking tool in 92.2% of the overall cases evaluated, 12.2 percentage points more than the best technique currently available. Moreover, the superiority of MAAT over the state-of-the-art holds on all the tasks and measurements that we study. We have made publicly available the code and data of this work to allow for future replication and extension.
@inproceedings{paperbot7042,
title = {MAAT: a novel ensemble approach to addressing fairness and performance bugs for machine learning software},
author = {Zhenpeng Chen and Jie M. Zhang and Federica Sarro and Mark Harman},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3549093}
}