SAFER is a continual unlearning method that prevents progressive accuracy loss on retain data and reversal of forgetting by enforcing representation stability and negative logit margins.
9 drives its unlearning margin toward negative values: U M(x)<0.(15) Thus, forgotten samples remain suboptimal within the decision space
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
-
Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal
SAFER is a continual unlearning method that prevents progressive accuracy loss on retain data and reversal of forgetting by enforcing representation stability and negative logit margins.