ExMap facilitates group-robustness by extracting explainability heatmaps from the frozen base ERM model for the validation data (A). These heatmaps are then clustered (B) to obtain pseudo-labels for the underlying groups, which are subsequently chosen for the retraining strategy (C).

Blog

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations

October 3, 2024

Publication

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations

March 20, 2024

Chakraborty, Rwiddhi; Sletten, Adrian; Kampffmeyer, Michael Christian.

Paper abstract

Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the groups, which is time-consuming and expensive to obtain. As a result, unsupervised group robustness strategies are sought. Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers. ExMap utilizes a clustering module to infer pseudo-labels based on a model's explainability heatmaps, which are then used during training in lieu of actual labels. Our empirical studies validate the efficacy of ExMap - We demonstrate that it bridges the performance gap with its supervised counterparts and outperforms existing partially supervised and unsupervised methods. Additionally, ExMap can be seamlessly integrated with existing group robustness learning strategies. Finally, we demonstrate its potential in tackling the emerging issue of multiple shortcut mitigation