Asynchronous Wireless Federated Learning with Probabilistic Client Selection
This work addresses efficiency and energy concerns in wireless federated learning for distributed clients, but it is incremental as it builds on existing asynchronous FL methods.
The paper tackles the stragglers issue in asynchronous federated learning by introducing probabilistic client selection and bandwidth allocation, optimizing the trade-off between convergence rate and energy consumption, with experiments showing superiority over traditional schemes.
Federated learning (FL) is a promising distributed learning framework where distributed clients collaboratively train a machine learning model coordinated by a server. To tackle the stragglers issue in asynchronous FL, we consider that each client keeps local updates and probabilistically transmits the local model to the server at arbitrary times. We first derive the (approximate) expression for the convergence rate based on the probabilistic client selection. Then, an optimization problem is formulated to trade off the convergence rate of asynchronous FL and mobile energy consumption by joint probabilistic client selection and bandwidth allocation. We develop an iterative algorithm to solve the non-convex problem globally optimally. Experiments demonstrate the superiority of the proposed approach compared with the traditional schemes.