FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks

2025-09-23

AI Summary

To address communication bottlenecks and training latency arising from overlapping coverage of edge servers in multi-server federated learning, this paper proposes FedOC—a novel framework leveraging inherent wireless edge network overlap. FedOC introduces a dual-role mechanism for clients in overlapping regions, enabling them to act either as relays or standard participants. This supports real-time cross-server model forwarding, latency-aware dynamic model selection, and two-phase aggregation—thereby facilitating decentralized inter-cell model propagation and implicit data fusion without additional infrastructure. The design fully exploits the natural coverage overlap in wireless edge networks. Extensive experiments demonstrate that FedOC significantly outperforms state-of-the-art approaches in both convergence speed and final model accuracy, achieving up to 32.7% reduction in end-to-end training latency. Its lightweight, infrastructure-free architecture makes it particularly suitable for ultra-low-latency edge intelligence applications.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Multi-server Federated Learning (FL) has emerged as a promising solution to mitigate communication bottlenecks of single-server FL. We focus on a typical multi-server FL architecture, where the regions covered by different edge servers (ESs) may overlap. A key observation of this architecture is that clients located in the overlapping areas can access edge models from multiple ESs. Building on this insight, we propose FedOC (Federated learning with Overlapping Clients), a novel framework designed to fully exploit the potential of these overlapping clients. In FedOC, overlapping clients could serve dual roles: (1) as Relay Overlapping Clients (ROCs), they forward edge models between neighboring ESs in real time to facilitate model sharing among different ESs; and (2) as Normal Overlapping Clients (NOCs), they dynamically select their initial model for local training based on the edge model delivery time, which enables indirect data fusion among different regions of ESs. The overall FedOC workflow proceeds as follows: in every round, each client trains local model based on the earliest received edge model and transmits to the respective ESs for model aggregation. Then each ES transmits the aggregated edge model to neighboring ESs through ROC relaying. Upon receiving the relayed models, each ES performs a second aggregation and subsequently broadcasts the updated model to covered clients. The existence of ROCs enables the model of each ES to be disseminated to the other ESs in a decentralized manner, which indirectly achieves intercell model and speeding up the training process, making it well-suited for latency-sensitive edge environments. Extensive experimental results show remarkable performance gains of our scheme compared to existing methods.

Problem

• Mitigating communication bottlenecks in single-server federated learning
• Exploiting overlapping clients in multi-server wireless edge networks
• Enabling decentralized model sharing to accelerate training process

Innovation

• Overlapping clients relay models between servers
• Clients train on earliest received edge models
• Servers perform dual aggregation with relayed models