Resource Allocation for Latency-Aware Federated Learning in Industrial Internet of Things

Abstract

Federated learning (FL) has been employed for numerous privacy-sensitive applications, where distributed devices collaboratively train a global model. In industrial Internet of things (IIoT) systems, training latency is the key performance metric as the automated manufacture usually requires timely processing. The existing works increase the number of effective devices to accelerate the training. However, devices in IIoT systems are usually deployed densely; increasing the number of clients can potentially cause serious interference and prolonged training latency. In this article, we propose a resource allocation scheme for FL, namely RaFed. We formulate the problem of reducing training latency as an optimization problem, which is proved to be NP-hard. We propose a heuristic algorithm to select appropriate devices for achieving a good tradeoff between the interference and convergence time. We conduct experiments using an RGB-D dataset in an IIoT system. The results show that RaFed significantly reduces the latency by 29.9%, compared to the state-of-the-art works.