Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mendieta, Matias, Sun, Guangyu, Chen, Chen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929647395012608
author Mendieta, Matias
Sun, Guangyu
Chen, Chen
author_facet Mendieta, Matias
Sun, Guangyu
Chen, Chen
contents Federated learning (FL) enables multiple clients to train models collectively while preserving data privacy. However, FL faces challenges in terms of communication cost and data heterogeneity. One-shot federated learning has emerged as a solution by reducing communication rounds, improving efficiency, and providing better security against eavesdropping attacks. Nevertheless, data heterogeneity remains a significant challenge, impacting performance. This work explores the effectiveness of diffusion models in one-shot FL, demonstrating their applicability in addressing data heterogeneity and improving FL performance. Additionally, we investigate the utility of our diffusion model approach, FedDiff, compared to other one-shot FL methods under differential privacy (DP). Furthermore, to improve generated sample quality under DP settings, we propose a pragmatic Fourier Magnitude Filtering (FMF) method, enhancing the effectiveness of generated data for global model training.
format Preprint
id arxiv_https___arxiv_org_abs_2405_01494
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
Mendieta, Matias
Sun, Guangyu
Chen, Chen
Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
Federated learning (FL) enables multiple clients to train models collectively while preserving data privacy. However, FL faces challenges in terms of communication cost and data heterogeneity. One-shot federated learning has emerged as a solution by reducing communication rounds, improving efficiency, and providing better security against eavesdropping attacks. Nevertheless, data heterogeneity remains a significant challenge, impacting performance. This work explores the effectiveness of diffusion models in one-shot FL, demonstrating their applicability in addressing data heterogeneity and improving FL performance. Additionally, we investigate the utility of our diffusion model approach, FedDiff, compared to other one-shot FL methods under differential privacy (DP). Furthermore, to improve generated sample quality under DP settings, we propose a pragmatic Fourier Magnitude Filtering (FMF) method, enhancing the effectiveness of generated data for global model training.
title Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
topic Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2405.01494