学术文献库

Federated learning (FL) is a technique for distributed machine learning (ML), in which edge devices carry out local model training on their individual datasets. In traditional FL algorithms, trained models at the edge are periodically sent to a central server for aggregation, utilizing a star topology as the underlying communication graph. However, assuming access to a central coordinator is not always practical, e.g., in ad hoc wireless network settings. In this paper, we develop a novel methodology for fully decentralized FL, where in addition to local training, devices conduct model aggregation via cooperative consensus formation with their one-hop neighbors over the decentralized underlying physical network. We further eliminate the need for a timing coordinator by introducing asynchronous, event-triggered communications among the devices. In doing so, to account for the inherent resource heterogeneity challenges in FL, we define personalized communication triggering conditions at each device that weigh the change in local model parameters against the available local resources. We theoretically demonstrate that our methodology converges to the globally optimal learning model at a $O{(\frac{\ln{k}}{\sqrt{k}})}$ rate under standard assumptions in distributed learning and consensus literature. Our subsequent numerical evaluations demonstrate that our methodology obtains substantial improvements in convergence speed and/or communication savings compared with existing decentralized FL baselines.