Open access
Aug 2026
FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
FedA2L is introduced, a method that dynamically adjusts layer-wise LRs based on model divergence signals that achieves up to 4.94 times faster convergence than vanilla DFL and reduces communication rounds by up to 59% compared to scheduler-based baselines.
V. T. Vo, K. Nguyen, Taehong Kim
· Future generations computer... · 0 citations