Saved in:
Bibliographic Details
Main Authors: Zhang, Jie, Qi, Xiaohua, Zhao, Bo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.16064
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913372260270080
author Zhang, Jie
Qi, Xiaohua
Zhao, Bo
author_facet Zhang, Jie
Qi, Xiaohua
Zhao, Bo
contents Existing approaches in Federated Learning (FL) mainly focus on sending model parameters or gradients from clients to a server. However, these methods are plagued by significant inefficiency, privacy, and security concerns. Thanks to the emerging foundation generative models, we propose a novel federated learning framework, namely Federated Generative Learning. In this framework, each client can create text embeddings that are tailored to their local data, and send embeddings to the server. Then the informative training data can be synthesized remotely on the server using foundation generative models with these embeddings, which can benefit FL tasks. Our proposed framework offers several advantages, including increased communication efficiency, robustness to data heterogeneity, substantial performance improvements, and enhanced privacy protection. We validate these benefits through extensive experiments conducted on 12 datasets. For example, on the ImageNet100 dataset with a highly skewed data distribution, our method outperforms FedAvg by 12% in a single communication round, compared to FedAvg's performance over 200 communication rounds. We have released the code for all experiments conducted in this study.
format Preprint
id arxiv_https___arxiv_org_abs_2306_16064
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Federated Generative Learning with Foundation Models
Zhang, Jie
Qi, Xiaohua
Zhao, Bo
Machine Learning
Artificial Intelligence
Existing approaches in Federated Learning (FL) mainly focus on sending model parameters or gradients from clients to a server. However, these methods are plagued by significant inefficiency, privacy, and security concerns. Thanks to the emerging foundation generative models, we propose a novel federated learning framework, namely Federated Generative Learning. In this framework, each client can create text embeddings that are tailored to their local data, and send embeddings to the server. Then the informative training data can be synthesized remotely on the server using foundation generative models with these embeddings, which can benefit FL tasks. Our proposed framework offers several advantages, including increased communication efficiency, robustness to data heterogeneity, substantial performance improvements, and enhanced privacy protection. We validate these benefits through extensive experiments conducted on 12 datasets. For example, on the ImageNet100 dataset with a highly skewed data distribution, our method outperforms FedAvg by 12% in a single communication round, compared to FedAvg's performance over 200 communication rounds. We have released the code for all experiments conducted in this study.
title Federated Generative Learning with Foundation Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2306.16064