FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Zhenyu, Feng, Wanglei, Wu, Di, Hu, Haozhen, Xu, Chang, Qian, Bin, Hong, Zhen, Wang, Cong, Ji, Shouling
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913580111101952
author Wen, Zhenyu
Feng, Wanglei
Wu, Di
Hu, Haozhen
Xu, Chang
Qian, Bin
Hong, Zhen
Wang, Cong
Ji, Shouling
author_facet Wen, Zhenyu
Feng, Wanglei
Wu, Di
Hu, Haozhen
Xu, Chang
Qian, Bin
Hong, Zhen
Wang, Cong
Ji, Shouling
contents Federated Learning (FL), as a mainstream privacy-preserving machine learning paradigm, offers promising solutions for privacy-critical domains such as healthcare and finance. Although extensive efforts have been dedicated from both academia and industry to improve the vanilla FL, little work focuses on the data pricing mechanism. In contrast to the straightforward in/post-training pricing techniques, we study a more difficult problem of pre-training pricing without direct information from the learning process. We propose FLMarket that integrates a two-stage, auction-based pricing mechanism with a security protocol to address the utility-privacy conflict. Through comprehensive experiments, we show that the client selection according to FLMarket can achieve more than 10% higher accuracy in subsequent FL training compared to state-of-the-art methods. In addition, it outperforms the in-training baseline with more than 2% accuracy increase and 3x run-time speedup.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11713
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learning
Wen, Zhenyu
Feng, Wanglei
Wu, Di
Hu, Haozhen
Xu, Chang
Qian, Bin
Hong, Zhen
Wang, Cong
Ji, Shouling
Machine Learning
Distributed, Parallel, and Cluster Computing
Federated Learning (FL), as a mainstream privacy-preserving machine learning paradigm, offers promising solutions for privacy-critical domains such as healthcare and finance. Although extensive efforts have been dedicated from both academia and industry to improve the vanilla FL, little work focuses on the data pricing mechanism. In contrast to the straightforward in/post-training pricing techniques, we study a more difficult problem of pre-training pricing without direct information from the learning process. We propose FLMarket that integrates a two-stage, auction-based pricing mechanism with a security protocol to address the utility-privacy conflict. Through comprehensive experiments, we show that the client selection according to FLMarket can achieve more than 10% higher accuracy in subsequent FL training compared to state-of-the-art methods. In addition, it outperforms the in-training baseline with more than 2% accuracy increase and 3x run-time speedup.
title FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learning
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2411.11713