GeFL: Model-Agnostic Federated Learning with Generative Models

TL;DR

This paper introduces GeFL, a federated learning framework using generative models for knowledge sharing across heterogeneous client models, addressing scalability and privacy issues with an improved variant GeFL-F.

Contribution

The paper proposes a novel generative model-based federated learning framework that supports model heterogeneity and introduces an enhanced version, GeFL-F, to improve scalability and privacy.

Findings

GeFL achieves competitive performance in heterogeneous federated learning scenarios.

GeFL-F improves scalability and reduces privacy risks compared to the original GeFL.

Extensive experiments validate the effectiveness of both methods across image classification tasks.

Abstract

Federated learning (FL) is a distributed training paradigm that enables collaborative learning across clients without sharing local data, thereby preserving privacy. However, the increasing scale and complexity of modern deep models often exceed the computational or memory capabilities of edge devices. Furthermore, clients may be constrained to use heterogeneous model architectures due to hardware variability (e.g., ASICs, FPGAs) or proprietary requirements that prevent the disclosure or modification of local model structures. These practical considerations motivate the need for model-heterogeneous FL, where clients participate using distinct model architectures. In this work, we propose Generative Model-Aided Federated Learning (GeFL), a framework that enables cross-client knowledge sharing via a generative model trained in a federated manner. This generative model captures global data semantics and facilitates local training without requiring model homogeneity across clients. While GeFL achieves strong performance, empirical analysis reveals limitations in scalability and potential privacy leakage due to generative sample memorization. To address these concerns, we propose GeFL-F, which utilizes feature-level generative modeling. This approach enhances scalability to large client populations and mitigates privacy risks. Extensive experiments across image classification tasks demonstrate that both GeFL and GeFL-F offer competitive performance in heterogeneous settings. Code is available at [1].