A dual data and loss-centric method claims to speed up machine unlearning, but its MIA regularizer cancels itself and the test set is leaked into training.
Can bad teaching induce forgetting? unlearning in deep networks using an incompetent teacher
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Leveraging Distribution Matching to Make Approximate Machine Unlearning Faster
A dual data and loss-centric method claims to speed up machine unlearning, but its MIA regularizer cancels itself and the test set is leaked into training.