Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout. (arXiv:2210.16105v1 [cs.LG])

Asynchronous learning protocols have regained attention lately, especially in
the Federated Learning (FL) setup, where slower clients can severely impede the
learning process. Herein, we propose \texttt{AsyncDrop}, a novel asynchronous
FL framework that utilizes dropout regularization to handle device
heterogeneity in distributed settings. Overall, \texttt{AsyncDrop} achieves
better performance compared to state of the art asynchronous methodologies,
while resulting in less communication and training time overheads. The key idea
revolves around creating ``submodels'' out of the global model, and
distributing their …

arxiv asynchronous distributed dropout federated learning light