FedEve uses a Kalman filter to combine server momentum (prediction) with client updates (observation) to offset period drift and client drift in cross-device federated learning.
A general theory for client sampling in federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning
FedEve uses a Kalman filter to combine server momentum (prediction) with client updates (observation) to offset period drift and client drift in cross-device federated learning.