A 'healing' procedure that uses similar real examples as surrogates for unlearned data during fine-tuning mitigates accuracy loss from machine unlearning in several classification benchmarks.
California consumer privacy act of 2018, 2018
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
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
How to Protect Models against Adversarial Unlearning?
A 'healing' procedure that uses similar real examples as surrogates for unlearned data during fine-tuning mitigates accuracy loss from machine unlearning in several classification benchmarks.