FedAH improves personalized federated learning by element-wise mixing each client's local head with the global head before local training, and it reports better accuracy than ten federated baselines on five benchmarks.
Fedcp: Separating feature information for personalized federated learn- ing via conditional policy,
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
background 1representative citing papers
citing papers explorer
-
FedAH: Aggregated Head for Personalized Federated Learning
FedAH improves personalized federated learning by element-wise mixing each client's local head with the global head before local training, and it reports better accuracy than ten federated baselines on five benchmarks.