Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

Excerpt

arXiv:2610.01028v1 Announce Type: new Abstract: 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 subseq