Conference
Open access
Sep 2026
Learning Local Feature Masks with Variational Information Bottleneck
VIBMask is proposed, a unified IWFS framework by the variational information bottleneck that mitigates co-adaptation by penalizing mutual information between unselected features and the label, and improves expressivity via an ensemble of diverse selectors that capture heterogeneous sparse patterns.
Lu Sun, Jun Sakuma
· Proceedings of the Thirty-Fi... · 0 citations