FedA2L adapts per-layer learning rates from local weight-divergence and aggregation-stability signals, accelerating convergence in decentralized federated learning without extra communication.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
FedA2L adapts per-layer learning rates from local weight-divergence and aggregation-stability signals, accelerating convergence in decentralized federated learning without extra communication.