HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations

ArXi:2603.29313v1 Announce Type: new Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have shown that, even in such settings, the feature extractor of an Empirical Risk Minimization (ERM)-trained model can a lightweight head while keeping the backbone frozen can substantially improve performance on shifted distributions and minority groups.