Tag
This paper argues that standard output-level evaluations of machine unlearning overestimate success, showing that methods can appear successful at the output layer while retaining structured representation-level discrepancies relative to retrained models. The authors propose retraining-consistent representation forgetting as a stronger evaluative lens.
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.