Towards Flexible Device Participation in Federated Learning

TL;DR

This paper proposes a flexible federated learning framework that accommodates device inactivity, incomplete updates, and dynamic participation, enhancing convergence and scalability in non-IID data environments.

Contribution

It introduces a new aggregation scheme and analytical insights enabling federated learning to handle more realistic device participation scenarios.

Findings

Flexible participation improves convergence in non-IID settings.

The new scheme tolerates inactive devices and incomplete updates.

Analysis shows robustness to device arrivals and departures.

Abstract

Traditional federated learning algorithms impose strict requirements on the participation rates of devices, which limit the potential reach of federated learning. This paper extends the current learning paradigm to include devices that may become inactive, compute incomplete updates, and depart or arrive in the middle of training. We derive analytical results to illustrate how allowing more flexible device participation can affect the learning convergence when data is not independently and identically distributed (non-IID). We then propose a new federated aggregation scheme that converges even when devices may be inactive or return incomplete updates. We also study how the learning process can adapt to early departures or late arrivals, and analyze their impacts on the convergence.