Efficient Federated Learning with Timely Update Dissemination

TL;DR

This paper introduces FedASMU and FedSSMU, innovative federated learning methods that leverage additional bandwidth for timely updates, achieving significant improvements in accuracy and efficiency through asynchronous and synchronous frameworks.

Contribution

The paper presents novel asynchronous and synchronous federated learning frameworks that utilize extra bandwidth resources for faster, more accurate model updates with proven convergence.

Findings

FedASMU and FedSSMU outperform baseline methods in accuracy and efficiency.

Theoretical analysis confirms convergence of the proposed methods.

Extensive experiments on multiple datasets validate the effectiveness of the approaches.

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%).