最优传输重加权用于虚假相关与标签噪声下的稳健学习
Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
浏览论文内容
中文总结 AI 辅助
针对虚假相关与标签噪声下的子群体偏移问题，提出基于最优传输的POTER重加权框架，通过传输几何度量样本重要性，仅需单阶段ERM训练，在标准基准上实现最先进的组内最差精度。
中文摘要 AI 辅助
机器学习模型在子群体偏移下常常出现性能下降，尤其是当虚假相关导致模型依赖无法跨子群体泛化的捷径特征时。近期一系列工作通过基于损失的信号来识别信息量大的样本以缓解该问题，但这些信号在标签噪声下可能被严重扭曲：错误标记的样本也可能产生较大损失，从而污染后续的重加权或重训练过程。尽管这一问题具有实际重要性，但该交叉领域在很大程度上仍未得到充分探索。我们提出POTER，一种基于最优传输的重加权框架，它从训练分布与由有限验证组标注构建的参考分布之间的传输几何中推导样本重要性。通过在个体样本层面衡量对齐程度而非依赖损失，POTER降低错误标记或强烈偏向对齐样本的权重，同时赋予与参考分布更对齐的样本更高的重要性。此外，POTER仅需单一ERM训练阶段，超越了近期工作中常见的重训练范式。在标准基准和噪声标签设置下，POTER实现了最先进的组内最差精度，包括标签损坏集中在少数子群体中的情况。
英文摘要
Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely on shortcut features that fail to generalize across subgroups. A recent line of work mitigates this issue by using loss-based signals to identify informative samples, but these signals can become severely distorted under label noise: mislabeled samples may also incur large losses and contaminate subsequent reweighting or retraining. Despite its practical importance, this intersection remains largely underexplored. We propose POTER, a reweighting framework based on optimal transport that derives sample importance from the transport geometry between the training distribution and a reference distribution constructed from limited validation group annotations. By measuring alignment at the individual-sample level rather than relying on loss, POTER downweights mislabeled or strongly bias-aligned samples while assigning higher importance to samples better aligned with the reference distribution. In addition, POTER requires only a single ERM training stage, moving beyond the retraining paradigm common in recent work. Across standard benchmarks and noisy-label settings, POTER achieves state-of-the-art worst-group accuracy, including cases where label corruption is concentrated within minority subgroups.
发表机构
- Pohang University of Science and Technology (POSTECH)（浦项科技大学）
机构由 AI 辅助整理，请以论文原文为准。
