HyperFedNet: Communication-Efficient Personalized Federated Learning Via Hypernetwork

TL;DR

HyperFedNet introduces a hypernetwork-based federated learning architecture that reduces communication costs and enhances privacy by transmitting fewer parameters and dynamically generating local model parameters.

Contribution

It proposes a novel hypernetwork approach for federated learning that improves communication efficiency and privacy protection over traditional methods.

Findings

Reduces communication overhead significantly.

Improves model accuracy in non-IID data settings.

Enhances privacy by transmitting fewer parameters.

Abstract

In response to the challenges posed by non-independent and identically distributed (non-IID) data and the escalating threat of privacy attacks in Federated Learning (FL), we introduce HyperFedNet (HFN), a novel architecture that incorporates hypernetworks to revolutionize parameter aggregation and transmission in FL. Traditional FL approaches, characterized by the transmission of extensive parameters, not only incur significant communication overhead but also present vulnerabilities to privacy breaches through gradient analysis. HFN addresses these issues by transmitting a concise set of hypernetwork parameters, thereby reducing communication costs and enhancing privacy protection. Upon deployment, the HFN algorithm enables the dynamic generation of parameters for the basic layer of the FL main network, utilizing local database features quantified by embedding vectors as input. Through extensive experimentation, HFN demonstrates superior performance in reducing communication overhead and improving model accuracy compared to conventional FL methods. By integrating the HFN algorithm into the FL framework, HFN offers a solution to the challenges of non-IID data and privacy threats.