SOURCE-LINKED INTELLIGENCE

SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Spurious correlations pose a significant challenge to the robustness of modern machine learning. The inherent imbalance in dataset distributions often leads traditional Empirical Risk Minimization (ERM) models to rely on majority spurious attributes for classification, resulting in poor performance on minority groups. This problem becomes particularly challenging when the spurious attributes are unavailable. Existing group-label-free methods often upsample minority groups or misclassified real training examples; repeating the same instances can reduce effective diversity and encourage overfitt

Read original source ↗ Open in workspace

recordType

paper

region

Global