Tag
The paper introduces Sharp Mode Connectivity (SMC) to enhance the robustness of weight-space interpolation in neural networks by optimizing for flatness along entire paths, achieving significant accuracy improvements under distribution shifts.
This paper proposes ManiF-SMC, a method for approximate machine unlearning that operates entirely in the representation space by pushing erased samples away from their original learned manifold representation toward their nearest semantic neighbors in the retained data, using a margin-based triplet loss guided by a self-mode-connectivity module for adaptive margins.