提出分层鲁棒学习方法，同时应对组间与组内分布偏移。
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
- 构建分层不确定性集，兼顾组间与组内分布变化
- 在少数群体分布偏移场景下表现显著优于现有方法
- 适合处理数据稀疏的少数群体鲁棒学习问题
传统监督学习方法在测试数据分布偏移时易受虚假相关性影响。尽管群组分布鲁棒优化（Group DRO）对子群体偏移具有强鲁棒性，但在样本少的少数群体中仍难以应对组内分布变化。本文提出一种分层扩展的Group DRO方法，同时建模组间与组内不确定性，实现多层级分布偏移的鲁棒性。我们还引入新基准，模拟真实世界中少数群体的分布偏移——这一关键挑战此前未被充分研究。实验表明，该方法在现有方法普遍失效的条件下仍保持优异鲁棒性，且在标准基准上性能更优。结果凸显了扩展不确定性集以涵盖多层级分布不确定性的必要性。
原文摘要 · Abstract (English)
Conventional supervised learning methods are often vulnerable to spurious correlations, particularly under distribution shifts in test data. To address this issue, several approaches, most notably Group DRO, have been developed. While these methods are highly robust to subpopulation or group shifts, they remain vulnerable to intra-group distributional shifts, which frequently occur in minority groups with limited samples. We propose a hierarchical extension of Group DRO that addresses both inter-group and intra-group uncertainties, providing robustness to distribution shifts at multiple levels. We also introduce new benchmark settings that simulate realistic minority group distribution shifts-an important yet previously underexplored challenge in spurious correlation research. Our method demonstrates strong robustness under these conditions-where existing robust learning methods consistently fail-while also achieving superior performance on standard benchmarks. These results highlight the importance of broadening the ambiguity set to better capture both inter-group and intra-group distributional uncertainties.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。