Subgroups matter for robust bias mitigation

Conference item

Despite the constant development of new bias mitigation methods for machine learning, no method consistently succeeds, and a fundamental question remains unanswered: when and why do bias mitigation techniques fail? In this paper, we hypothesise that a key factor may be the often-overlooked but crucial step shared by many bias mitigation methods: the definition of subgroups. To investigate this, we conduct a comprehensive evaluation of state-of-the-art bias mitigation methods across multiple vision and language classification tasks, systematically varying subgroup definitions, including coarse, fine-grained, intersectional, and noisy subgroups. Our findings reveal that subgroup choice significantly impacts performance, with certain groupings paradoxically leading to worse outcomes than no mitigation at all. They suggest that observing a disparity between a set of subgroups is not a sufficient reason to use those subgroups for mitigation. Through theoretical analysis, we explain these phenomena and uncover a counter-intuitive insight that, in some cases, improving fairness with respect to a particular set of subgroups is best achieved by using a different set of subgroups for mitigation. Our work highlights the importance of careful subgroup definition in bias mitigation and presents it as an alternative lever for improving the robustness and fairness of machine learning models.

Authors: Alloula, A; Jones, C; Glocker, B; Papież, BW

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: PMLR
• Host title: Proceedings of the 42nd International Conference on Machine Learning
• Series: Proceedings of Machine Learning Research
• Series number: 267
• Publication date: 2025-10-06
• Acceptance date: 2025-05-01
• Event title: 42nd International Conference on Machine Learning (ICML 2025)
• Event location: Vancouver, Canada
• Event website: https://icml.cc/Conferences/2025
• Event start date: 2025-07-13
• Event end date: 2025-07-19
• ISSN: 2640-3498
• Language: English