Asynchronous Diffusion Learning with Agent Subsampling and Local Updates
This work addresses asynchronous coordination in federated learning for distributed agents, but it appears incremental as it builds on existing diffusion strategies with specific modifications.
The paper tackles the problem of asynchronous federated learning with agent subsampling and local updates, proving stability in mean-square error and providing performance guarantees, as demonstrated through numerical simulations.
In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets. Our assumption is that each agent independently chooses when to participate throughout the algorithm and the specific subset of its neighbourhood with which it will cooperate at any given moment. When an agent chooses to take part, it undergoes multiple local updates before conveying its outcomes to the sub-sampled neighbourhood. Under this setup, we prove that the resulting asynchronous diffusion strategy is stable in the mean-square error sense and provide performance guarantees specifically for the federated learning setting. We illustrate the findings with numerical simulations.