Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations: R. Chakraborty

Rwiddhi Chakraborty, a doctoral research fellow at UiT Machine Learning Group, gave a presentation titled "ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations" in our Visual Intelligence Online Seminar series (April 25th 2024).
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 intraditional classifiers. ExMap utilizes a clustering module to inferpseudo-labels based on a model's explainability heat maps, 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.