ISPF combines a new generator loss that discourages synthesis of forgetting-class samples with a logit-redistribution step that lets every synthetic sample contribute to distillation, improving retained accuracy over GKT.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward Efficient Data-Free Unlearning
ISPF combines a new generator loss that discourages synthesis of forgetting-class samples with a logit-redistribution step that lets every synthetic sample contribute to distillation, improving retained accuracy over GKT.