On differential privacy for federated learning in wireless systems with multiple base stations

Abstract In this work, we consider a federated learning model in a wireless system with multiple base stations and inter‐cell interference. We apply a differentially private scheme to transmit information from users to their corresponding base station during the learning phase. We show the convergen...

Full description

Saved in:
Bibliographic Details
Main Authors: Nima Tavangaran, Mingzhe Chen, Zhaohui Yang, José Mairton B. Da Silva Jr., H. Vincent Poor
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Communications
Subjects:
Online Access:https://doi.org/10.1049/cmu2.12722
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054163715588096
author Nima Tavangaran
Mingzhe Chen
Zhaohui Yang
José Mairton B. Da Silva Jr.
H. Vincent Poor
author_facet Nima Tavangaran
Mingzhe Chen
Zhaohui Yang
José Mairton B. Da Silva Jr.
H. Vincent Poor
author_sort Nima Tavangaran
collection DOAJ
description Abstract In this work, we consider a federated learning model in a wireless system with multiple base stations and inter‐cell interference. We apply a differentially private scheme to transmit information from users to their corresponding base station during the learning phase. We show the convergence behavior of the learning process by deriving an upper bound on its optimality gap. Furthermore, we define an optimization problem to reduce this upper bound and the total privacy leakage. To find the locally optimal solutions of this problem, we first propose an algorithm that schedules the resource blocks and users. We then extend this scheme to reduce the total privacy leakage by optimizing the differential privacy artificial noise. We apply the solutions of these two procedures as parameters of a federated learning system where each user is equipped with a classifier and communication cells have mostly fewer resource blocks than numbers of users. The simulation results show that our proposed scheduler improves the average accuracy of the predictions compared with a random scheduler. In particular, the results show an improvement of over 6%. Furthermore, its extended version with noise optimizer significantly reduces the amount of privacy leakage.
format Article
id doaj-art-b95d6b1304a04bee90ef575c5dc35012
institution DOAJ
issn 1751-8628
1751-8636
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Communications
spelling doaj-art-b95d6b1304a04bee90ef575c5dc350122025-08-20T02:52:20ZengWileyIET Communications1751-86281751-86362024-12-0118201853186710.1049/cmu2.12722On differential privacy for federated learning in wireless systems with multiple base stationsNima Tavangaran0Mingzhe Chen1Zhaohui Yang2José Mairton B. Da Silva Jr.3H. Vincent Poor4Department of Electrical and Computer Engineering Princeton University Princeton New Jersey USADepartment of Electrical and Computer Engineering and Institute for Data Science and Computing University of Miami Coral Gables Florida USACollege of Information Science and Electronic Engineering Zhejiang University Hangzhou ChinaDepartment of Information Technology Uppsala University Uppsala SwedenDepartment of Electrical and Computer Engineering Princeton University Princeton New Jersey USAAbstract In this work, we consider a federated learning model in a wireless system with multiple base stations and inter‐cell interference. We apply a differentially private scheme to transmit information from users to their corresponding base station during the learning phase. We show the convergence behavior of the learning process by deriving an upper bound on its optimality gap. Furthermore, we define an optimization problem to reduce this upper bound and the total privacy leakage. To find the locally optimal solutions of this problem, we first propose an algorithm that schedules the resource blocks and users. We then extend this scheme to reduce the total privacy leakage by optimizing the differential privacy artificial noise. We apply the solutions of these two procedures as parameters of a federated learning system where each user is equipped with a classifier and communication cells have mostly fewer resource blocks than numbers of users. The simulation results show that our proposed scheduler improves the average accuracy of the predictions compared with a random scheduler. In particular, the results show an improvement of over 6%. Furthermore, its extended version with noise optimizer significantly reduces the amount of privacy leakage.https://doi.org/10.1049/cmu2.127226Gdata privacyfederated learningoptimizationschedulingwireless channels
spellingShingle Nima Tavangaran
Mingzhe Chen
Zhaohui Yang
José Mairton B. Da Silva Jr.
H. Vincent Poor
On differential privacy for federated learning in wireless systems with multiple base stations
IET Communications
6G
data privacy
federated learning
optimization
scheduling
wireless channels
title On differential privacy for federated learning in wireless systems with multiple base stations
title_full On differential privacy for federated learning in wireless systems with multiple base stations
title_fullStr On differential privacy for federated learning in wireless systems with multiple base stations
title_full_unstemmed On differential privacy for federated learning in wireless systems with multiple base stations
title_short On differential privacy for federated learning in wireless systems with multiple base stations
title_sort on differential privacy for federated learning in wireless systems with multiple base stations
topic 6G
data privacy
federated learning
optimization
scheduling
wireless channels
url https://doi.org/10.1049/cmu2.12722
work_keys_str_mv AT nimatavangaran ondifferentialprivacyforfederatedlearninginwirelesssystemswithmultiplebasestations
AT mingzhechen ondifferentialprivacyforfederatedlearninginwirelesssystemswithmultiplebasestations
AT zhaohuiyang ondifferentialprivacyforfederatedlearninginwirelesssystemswithmultiplebasestations
AT josemairtonbdasilvajr ondifferentialprivacyforfederatedlearninginwirelesssystemswithmultiplebasestations
AT hvincentpoor ondifferentialprivacyforfederatedlearninginwirelesssystemswithmultiplebasestations