EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks

2026-03-02

AI Summary

This work addresses the high communication overhead and latency inherent in traditional cloud-based federated learning, which are particularly pronounced in Internet of Things (IoT) edge scenarios. The authors propose the first serverless federated learning framework based on sequential model migration among edge base stations, eliminating the need for cloud coordination by reconstructing the system topology through successive model passing and aggregation at the edge. The approach accommodates non-convex objectives and non-independent and identically distributed (non-IID) data, for which the paper establishes rigorous convergence guarantees. Extensive experiments across diverse configurations demonstrate that the method achieves model accuracy comparable to conventional approaches while substantially reducing global communication costs.

Technology Category

Machine Learning: Learning on the Edge & Model CompressionSearch and Optimization: Learning to SearchComputer 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 processingUser Modeling, Personalization and Recommendation: Federated recommendation systems and personalizationGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Federated Learning (FL) has emerged as a transformative distributed learning paradigm in the era of Internet of Things (IoT), reconceptualizing data processing methodologies. However, FL systems face significant communication bottlenecks due to inevitable client-server data exchanges and long-distance transmissions. This work presents EdgeFLow, an innovative FL framework that redesigns the system topology by replacing traditional cloud servers with sequential model migration between edge base stations. By conducting model aggregation and propagation exclusively at edge clusters, EdgeFLow eliminates cloud-based transmissions and substantially reduces global communication overhead. We provide rigorous convergence analysis for EdgeFLow under non-convex objectives and non-IID data distributions, extending classical FL convergence theory. Experimental results across various configurations validate the theoretical analysis, demonstrating that EdgeFLow achieves comparable accuracy improvements while significantly reducing communication costs. As a systemic architectural innovation for communication-efficient FL, EdgeFLow establishes a foundational framework for future developments in IoT and edge-network learning systems.

Problem

• Federated Learning
• communication bottleneck
• edge networks
• IoT
• serverless

Innovation

• Serverless Federated Learning
• Sequential Model Migration
• Edge Computing
• Communication Efficiency
• Convergence Analysis