一句话：提出 GRFT，通过遗传算法增强全局搜索、轻量随机局部搜索，并基于适应度修复，显著提升个体歧视测试与修复效果。
深度学习在关键决策应用中表现突出，但可能产生不公平行为，其中个体歧视（仅敏感属性不同、其余画像相同的实例对之间的不平等）社会影响尤为严重。现有部署前个体歧视测试方法虽多，但效率和有效性仍有限，尤其在较公平模型上，且尚不清楚测试框架中全局阶段与局部阶段何者为主要瓶颈。本文首先识别出增强全局阶段比增强局部阶段更能持续提升整体测试效果，进而提出 Genetic-Random Fairness Testing (GRFT)：全局阶段用遗传算法引导搜索更多具有歧视性的实例，局部阶段采用轻量随机搜索探索这些实例的邻居以避免耗时计算；此外基于适应度分数提出一种直接有效的修复方法。实验涵盖 6 种测试方法、5 个数据集、261 个模型（5 个朴素训练、64 个修复、192 个量化用于端侧部署）以及 16 种敏感属性组合，表明 GRFT 与所提修复方法具有优越性能。
Deep Learning (DL) has achieved significant success in socially critical decision-making applications but often exhibits unfair behaviors, raising social concerns. Among these unfair behaviors, individual discrimination-examining inequalities between instance pairs with identical profiles differing only in sensitive attributes such as gender, race, and age-is extremely socially impactful. Existing methods have made significant and commendable efforts in testing individual discrimination before deployment. However, their efficiency and effectiveness remain limited, particularly when evaluating relatively fairer models. It remains unclear which phase of the existing testing framework (global or local) is the primary bottleneck limiting performance. Facing the above issues, we first identify that enhancing the global phase consistently improves overall testing effectiveness compared to enhancing the local phase. This motivates us to propose Genetic-Random Fairness Testing (GRFT), an effective and efficient method. In the global phase, we use a genetic algorithm to guide the search for more global discriminatory instances. In the local phase, we apply a light random search to explore the neighbors of these instances, avoiding time-consuming computations. Additionally, based on the fitness score, we also propose a straightforward yet effective repair approach. For a thorough evaluation, we conduct extensive experiments involving 6 testing methods, 5 datasets, 261 models (including 5 naively trained, 64 repaired, and 192 quantized for on-device deployment), and sixteen combinations of sensitive attributes, showing the superior performance of GRFT and our repair method.
@inproceedings{paperbot8697,
title = {Dissecting Global Search: A Simple Yet Effective Method to Boost Individual Discrimination Testing and Repair},
author = {Lili Quan and Tianlin Li and Xiaofei Xie and Zhenpeng Chen and Sen Chen and Lingxiao Jiang and Xiaohong Li},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00235}
}