Machine unlearning often creates an illusion of forgetting via feature-classifier misalignment, with hidden representations remaining discriminative; CMF-based methods enforce alignment for better representation-level unlearning.
[Yes] See Sections 2.1 and 4.3 for the main de- scription
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations
Machine unlearning often creates an illusion of forgetting via feature-classifier misalignment, with hidden representations remaining discriminative; CMF-based methods enforce alignment for better representation-level unlearning.