FedASA: A Personalized Federated Learning With Adaptive Model Aggregation for Heterogeneous Mobile Edge Computing

Federated learning (FL) opens a new promising paradigm for the Industrial Internet of Things (IoT) since it can collaboratively train machine learning models without sharing private data. However, deploying FL frameworks in real IoT scenarios faces three critical challenges, i.e., statistical heterogeneity, resource constraint, and fairness. To address these challenges, we design a fair and efficient FL method, termed FedASA, which can address the challenge of statistical heterogeneity in resource-constrained scenarios by determining the shared architecture adaptively. In FedASA, we first present a cell-wised shared architecture selection strategy, which can adaptively construct the shared architecture for each device. We then design a cell-based aggregation algorithm for aggregating heterogeneous shared architectures. In addition, we provide a theoretical analysis of the federated error bound, which provides a theoretical guarantee for the fairness. At the same time, we prove the convergence of FedASA at the first-order stationary point. We evaluate the performance of FedASA through extensive simulation and experiments. Experimental results in cross-location scenarios show that FedASA outperformed the state-of-the-art approaches, improving accuracy by up to 13.27% with better fairness and faster convergence and communication requirement has been reduced by 81.49%.

I. Introduction

With the advancement of mobile computing technology and the Internet of Things (IoT), industrial digitization and intelligence are rapidly progressing [1], [2], [3]. Intelligent applications in mobile edge computing (MEC) systems are supported by widely deployed edge devices (e.g., sensors) [4], [5]. As the number of sensors deployed increases, the data collected grows exponentially, resulting in a larger accumulation of data at the network edge (e.g., gateways and switches) [6], [7]. However, the network bandwidth burden is an obstacle to uploading data to the cloud for centralized learning [8], [9], [10]. Federated learning (FL) [11] emerges as a solution, allowing edge devices to train machine learning models collaboratively without transmitting private data to the parameter server. As such, FL has many promising applications in IoT, such as human activity recognition [12], [13], fault diagnosis [14], [15], [16], [17], and augmented reality [18].