Personalizing Federated Learning for Hierarchical Edge Networks with Non-IID Data

Zomaya School of Computer Science, The University of Sydney, Australia Department of Engineering Science, University of Oxford, United Kingdom School of Computing and Information Systems, The University of Melbourne, Australia Abstract --Accommodating edge networks between IoT devices and the cloud server in Hierarchical Federated Learning (HFL) enhances communication efficiency without compromising data privacy. However, devices connected to the same edge often share geographic or contextual similarities, leading to varying edge-level data heterogeneity with different subsets of labels per edge, on top of device-level heterogeneity. This hierarchical non-Independent and Identically Distributed (non-IID) nature, which implies that each edge has its own optimization goal, has been overlooked in HFL research. Therefore, existing edge-accommodated HFL demonstrates inconsistent performance across edges in various hierarchical non-IID scenarios. T o ensure robust performance with diverse edge-level non-IID data, we propose a Personalized Hierarchical Edge-enabled Federated Learning (PHE-FL), which personalizes each edge model to perform well on the unique class distributions specific to each edge. We evaluated PHE-FL across 4 scenarios with varying levels of edge-level non-IIDness, with extreme IoT device level non-IIDness. T o accurately assess the effectiveness of our personaliza-tion approach, we deployed test sets on each edge server instead of the cloud server, and used both balanced and imbalanced test sets. Extensive experiments show that PHE-FL achieves up to 83% higher accuracy compared to existing federated learning approaches that incorporate edge networks, given the same number of training rounds. Moreover, PHE-FL exhibits improved stability, as evidenced by reduced accuracy fluctuations relative to the state-of-the-art FedA vg with two-level (edge and cloud) aggregation. I NTRODUCTION Federated Learning (FL) is an emerging Machine Learning (ML) framework that achieves high accuracy without requiring the sharing of local data with a centralized server. Involving IoT devices and a central cloud server, 2-level FL aggregation framework was first proposed under the name FederatedAveraging (FedAvg) algorithm [1]. In FedAvg, IoT devices train models individually and then transmit the model weights to the cloud server. The server then averages these weights to create an aggregated global model that performs well and therefore can be deployed across all participating devices.