Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations

ArXi:2407.14974v2 Announce Type: replace Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations leads to poor performance in the data groups without these correlations and poor generalization ability. To improve the robustness of machine learning models to spurious correlations, we propose an approach to extract a subnetwork from a fully trained network that does not rely on spurious correlations.