Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning
Junhao Cai, Dohun Kim, Sung Il Choi +4
Source-free class unlearning erases whole classes using only the forget data, judged at the representation level, where features can leak a class the head no longer predicts. Exist…
cs.LG2026
Retain-Neutral Surrogates for Min-Max Unlearning
Junhao Cai, Dohun Kim, Dowon Kim +4
Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local edi…