pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning

TL;DR

This paper introduces pFedGPA, a diffusion-based generative framework for personalized federated learning that effectively captures complex parameter distributions and improves model performance over traditional aggregation methods.

Contribution

The paper proposes a novel diffusion model-based parameter aggregation method for personalized FL, addressing limitations of linear aggregation and enhancing personalization.

Findings

Outperforms baseline methods on multiple datasets.

Effectively captures complex parameter distributions.

Improves personalized model accuracy.

Abstract

Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions, potentially overlooking the complex, high-dimensional nature of the parameter space. This can result in degraded performance of the aggregated model. While personalized FL approaches can mitigate the heterogeneous data issue to some extent, the limitation of linear aggregation remains unresolved. To alleviate this issue, we investigate the generative approach of diffusion model and propose a novel generative parameter aggregation framework for personalized FL, \texttt{pFedGPA}. In this framework, we deploy a diffusion model on the server to integrate the diverse parameter distributions and propose a parameter inversion method to efficiently generate a set of personalized parameters for each client. This inversion method transforms the uploaded parameters into a latent code, which is then aggregated through denoising sampling to produce the final personalized parameters. By encoding the dependence of a client's model parameters on the specific data distribution using the high-capacity diffusion model, \texttt{pFedGPA} can effectively decouple the complexity of the overall distribution of all clients' model parameters from the complexity of each individual client's parameter distribution. Our experimental results consistently demonstrate the superior performance of the proposed method across multiple datasets, surpassing baseline approaches.