Oversampling the skewed class before recovery training restores federated unlearning model accuracy better than four baselines.
Federated unlearning and its privacy threats
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Federated Unlearning Model Recovery in Data with Skewed Label Distributions
Oversampling the skewed class before recovery training restores federated unlearning model accuracy better than four baselines.