GeFL: Model-Agnostic Federated Learning with Generative Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kang, Honggu, Cha, Seohyeon, Kang, Joonhyuk
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913843471450112
author Kang, Honggu
Cha, Seohyeon
Kang, Joonhyuk
author_facet Kang, Honggu
Cha, Seohyeon
Kang, Joonhyuk
contents 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].
format Preprint
id arxiv_https___arxiv_org_abs_2412_18460
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeFL: Model-Agnostic Federated Learning with Generative Models
Kang, Honggu
Cha, Seohyeon
Kang, Joonhyuk
Machine Learning
Artificial Intelligence
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].
title GeFL: Model-Agnostic Federated Learning with Generative Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.18460