FedOSD uses a bounded unlearning loss, an orthogonal steepest descent direction, and gradient projection in post-training to unlearn a federated learning client with little utility loss.
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
-
Federated Unlearning with Gradient Descent and Conflict Mitigation
FedOSD uses a bounded unlearning loss, an orthogonal steepest descent direction, and gradient projection in post-training to unlearn a federated learning client with little utility loss.