One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models

TL;DR

FedLMG introduces a novel federated learning approach that leverages local models and diffusion models to generate synthetic data, reducing client-side computation and effectively handling heterogeneity.

Contribution

The paper proposes FedLMG, a one-shot federated learning method that uses local models to guide diffusion models for synthetic data generation without requiring foundation models on clients.

Findings

Synthetic datasets are comparable in quality and diversity to real client data.

FedLMG outperforms existing methods and surpasses the performance ceiling.

Reduces computational requirements on client devices.

Abstract

In recent years, One-shot Federated Learning methods based on Diffusion Models have garnered increasing attention due to their remarkable performance. However, most of these methods require the deployment of foundation models on client devices, which significantly raises the computational requirements and reduces their adaptability to heterogeneous client models compared to traditional FL methods. In this paper, we propose FedLMG, a heterogeneous one-shot Federated learning method with Local Model-Guided diffusion models. Briefly speaking, in FedLMG, clients do not need access to any foundation models but only train and upload their local models, which is consistent with traditional FL methods. On the clients, we employ classification loss and BN loss to capture the broad category features and detailed contextual features of the client distributions. On the server, based on the uploaded client models, we utilize backpropagation to guide the server's DM in generating synthetic datasets that comply with the client distributions, which are then used to train the aggregated model. By using the locally trained client models as a medium to transfer client knowledge, our method significantly reduces the computational requirements on client devices and effectively adapts to scenarios with heterogeneous clients. Extensive quantitation and visualization experiments on three large-scale real-world datasets, along with theoretical analysis, demonstrate that the synthetic datasets generated by FedLMG exhibit comparable quality and diversity to the client datasets, which leads to an aggregated model that outperforms all compared methods and even the performance ceiling, further elucidating the significant potential of utilizing DMs in FL.