Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference

arXiv:2404.13815v1 Announce Type: new
Abstract: Standard empirical risk minimization (ERM) models may prioritize learning spurious correlations between spurious features and true labels, leading to poor accuracy on groups where these correlations do not hold. Mitigating this issue often requires expensive spurious attribute (group) labels or relies on trained ERM models to infer group labels when group information is unavailable. However, the significant performance gap in worst-group accuracy between using pseudo group labels and using oracle group labels inspires us to …

abstract accuracy arxiv correlation correlations cs.lg erm features improving inference issue labels risk robustness standard true type