Logg Inn
innsikt - Client Drift Mitigation in Federated Learning
FEDIMPRO: Measuring and Improving Client Update in Federated Learning at ICLR 2024
FedImpro aims to mitigate client drift in federated learning by constructing similar conditional distributions for local training, reducing gradient dissimilarity, and enhancing generalization performance.
FEDIMPRO: Measuring and Improving Client Update in Federated Learning at ICLR 2024
FEDIMPRO aims to mitigate client drift in federated learning by constructing similar conditional distributions for local training, reducing gradient dissimilarity, and enhancing generalization performance.
Produkter | Ressurser
© 2024 by Linnk AI