Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networks
This work addresses the practical deployment challenges of federated learning in cellular networks, which are characterized by unreliable communication and limited resources, for practitioners aiming to implement distributed machine learning.
This paper proposes a federated learning algorithm designed for unreliable and resource-constrained cellular wireless networks. The authors prove its convergence and derive an optimal scheduling policy to maximize the convergence rate, demonstrating its effectiveness through experiments on real and synthetic datasets.
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.