Efficient Federated Learning with Timely Update Dissemination

2025-07-08

AI Summary

To address model update latency, increased model staleness, slow global convergence, and degraded accuracy caused by limited downlink bandwidth in federated learning, this paper proposes two novel bandwidth-aware update dissemination mechanisms: the asynchronous framework FedASMU and the synchronous framework FedSSMU. FedASMU introduces server-side dynamic weighted aggregation, while FedSSMU employs client-side adaptive model fusion; both jointly mitigate gradient bias and local model drift. Extensive experiments across six models and five public benchmark datasets demonstrate that the proposed methods achieve up to a 145.87% improvement in test accuracy and a 97.59% increase in training efficiency. Moreover, they significantly enhance model consistency and convergence stability. This work establishes a new paradigm for bandwidth-scalable, efficient federated learning.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Mechanism Design
• Computer Vision: Diffusion Models for Vision

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Federated Learning (FL) has emerged as a compelling methodology for the management of distributed data, marked by significant advancements in recent years. In this paper, we propose an efficient FL approach that capitalizes on additional downlink bandwidth resources to ensure timely update dissemination. Initially, we implement this strategy within an asynchronous framework, introducing the Asynchronous Staleness-aware Model Update (FedASMU), which integrates both server-side and device-side methodologies. On the server side, we present an asynchronous FL system model that employs a dynamic model aggregation technique, which harmonizes local model updates with the global model to enhance both accuracy and efficiency. Concurrently, on the device side, we propose an adaptive model adjustment mechanism that integrates the latest global model with local models during training to further elevate accuracy. Subsequently, we extend this approach to a synchronous context, referred to as FedSSMU. Theoretical analyses substantiate the convergence of our proposed methodologies. Extensive experiments, encompassing six models and five public datasets, demonstrate that FedASMU and FedSSMU significantly surpass baseline methods in terms of both accuracy (up to 145.87%) and efficiency (up to 97.59%).

Problem

• Enhance FL efficiency using downlink bandwidth for timely updates
• Integrate server-side and device-side methods for better accuracy
• Propose synchronous and asynchronous FL approaches for improved performance

Innovation

• Asynchronous Staleness-aware Model Update (FedASMU)
• Dynamic model aggregation technique
• Adaptive model adjustment mechanism