SFU replaces the two usual federated unlearning steps with a single multi-teacher distillation objective that erases target classes in one or two rounds while keeping retained-data accuracy.
Zero- shot machine unlearning,
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
-
Streamlined Federated Unlearning: Unite as One to Be Highly Efficient
SFU replaces the two usual federated unlearning steps with a single multi-teacher distillation objective that erases target classes in one or two rounds while keeping retained-data accuracy.