Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networks

TL;DR

This paper introduces a federated learning algorithm tailored for unreliable, resource-limited cellular wireless networks, addressing real-world challenges and demonstrating its convergence through theoretical proofs and experiments.

Contribution

It proposes a novel federated learning algorithm optimized for cellular wireless environments, including convergence proof and optimal scheduling policy.

Findings

The algorithm converges under wireless network constraints.

Optimal scheduling enhances convergence rate.

Neglecting wireless unreliability leads to different problem solutions.

Abstract

With growth in the number of smart devices and advancements in their hardware, in recent years, data-driven machine learning techniques have drawn significant attention. However, due to privacy and communication issues, it is not possible to collect this data at a centralized location. Federated learning is a machine learning setting where the centralized location trains a learning model over remote devices. Federated learning algorithms cannot be employed in the real world scenarios unless they consider unreliable and resource-constrained nature of the wireless medium. In this paper, we propose a federated learning algorithm that is suitable for cellular wireless networks. We prove its convergence, and provide the optimal scheduling policy that maximizes the convergence rate. We also study the effect of local computation steps and communication steps on the convergence of the proposed algorithm. We prove, in practice, federated learning algorithms may solve a different problem than the one that they have been employed for if the unreliability of wireless channels is neglected. Finally, through numerous experiments on real and synthetic datasets, we demonstrate the convergence of our proposed algorithm.