一句话：提出 Fairea，用模型行为变异对偏见缓解方法进行基准测试，并大规模评估 12 种方法。
机器学习广泛应用使偏见（不公平）问题成为软件工程的重要关切，但偏见缓解方法的实际有效性缺乏系统基准。本文提出 Fairea，一种基于模型行为变异的偏见缓解方法基准测试方法，并开展大规模实证研究，评估 12 种广泛研究的偏见缓解方法。结果显示，这些方法在 49% 的情况下效果不佳；其中 15% 的缓解案例在公平性-准确率权衡上差于 Fairea 建立的基线；34% 的案例出现准确率下降且偏见增加。该工作为公平性缓解方法的评估提供了新思路，并揭示了常用方法在公平性与准确率权衡上的显著局限。
The increasingly wide uptake of Machine Learning (ML) has raised the significance of the problem of tackling bias (i.e., unfairness), making it a primary software engineering concern. In this paper, we introduce Fairea, a model behaviour mutation approach to benchmarking ML bias mitigation methods. We also report on a large-scale empirical study to test the effectiveness of 12 widely-studied bias mitigation methods. Our results reveal that, surprisingly, bias mitigation methods have a poor effectiveness in 49% of the cases. In particular, 15% of the mitigation cases have worse fairness-accuracy trade-offs than the baseline established by Fairea; 34% of the cases have a decrease in accuracy and an increase in bias.