Personalized Federated Learning using Hypernetworks

TL;DR

This paper introduces pFedHN, a hypernetwork-based method for personalized federated learning that generates individual models for clients, reduces communication costs, and improves generalization to new clients with different data distributions.

Contribution

The paper proposes a novel hypernetwork approach for personalized federated learning that enhances parameter sharing, reduces communication, and improves generalization to unseen clients.

Findings

pFedHN outperforms previous personalized federated learning methods.

Hypernetworks enable effective parameter sharing across clients.

The approach generalizes well to new clients with different data distributions.

Abstract

Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, while maintaining the capacity to generate unique and diverse personal models. Furthermore, since hypernetwork parameters are never transmitted, this approach decouples the communication cost from the trainable model size. We test pFedHN empirically in several personalized federated learning challenges and find that it outperforms previous methods. Finally, since hypernetworks share information across clients we show that pFedHN can generalize better to new clients whose distributions differ from any client observed during training.