ETID combines leave-one-out ensemble training with distillation-based unlearning to erase requested training samples while keeping model accuracy and consistency with retrained models.
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
-
From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models
ETID combines leave-one-out ensemble training with distillation-based unlearning to erase requested training samples while keeping model accuracy and consistency with retrained models.