Intelligent Client Selection for Federated Learning using Cellular Automata

TL;DR

This paper introduces a Cellular Automaton-based client selection algorithm for federated learning, which intelligently chooses clients based on resources and interactions, improving latency and efficiency in dynamic environments.

Contribution

The paper proposes a novel CA-CS algorithm that models client interactions and resources for improved client selection in federated learning.

Findings

CA-CS achieves similar accuracy to random selection.

CA-CS effectively avoids high-latency clients.

The method performs well on MNIST and CIFAR-10 datasets.

Abstract

Federated Learning (FL) has emerged as a promising solution for privacy-enhancement and latency minimization in various real-world applications, such as transportation, communications, and healthcare. FL endeavors to bring Machine Learning (ML) down to the edge by harnessing data from million of devices and IoT sensors, thus enabling rapid responses to dynamic environments and yielding highly personalized results. However, the increased amount of sensors across diverse applications poses challenges in terms of communication and resource allocation, hindering the participation of all devices in the federated process and prompting the need for effective FL client selection. To address this issue, we propose Cellular Automaton-based Client Selection (CA-CS), a novel client selection algorithm, which leverages Cellular Automata (CA) as models to effectively capture spatio-temporal changes in a fast-evolving environment. CA-CS considers the computational resources and communication capacity of each participating client, while also accounting for inter-client interactions between neighbors during the client selection process, enabling intelligent client selection for online FL processes on data streams that closely resemble real-world scenarios. In this paper, we present a thorough evaluation of the proposed CA-CS algorithm using MNIST and CIFAR-10 datasets, while making a direct comparison against a uniformly random client selection scheme. Our results demonstrate that CA-CS achieves comparable accuracy to the random selection approach, while effectively avoiding high-latency clients.