Reliable federated learning for mobile networks

Federated learning, as a promising machine learning approach, has emerged to leverage a distributed personalized dataset from a number of nodes, for example, mobile devices, to improve performance while simultaneously providing privacy preservation for mobile users. In federated learning, training d...

Full description

Bibliographic Details
Main Authors: Kang, Jiawen, Xiong, Zehui, Niyato, Dusit, Zou, Yuze, Zhang, Y., Guizani, M.
Other Authors: School of Computer Science and Engineering
Format: Journal Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/154439
_version_ 1826122510571143168
author Kang, Jiawen
Xiong, Zehui
Niyato, Dusit
Zou, Yuze
Zhang, Y.
Guizani, M.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Kang, Jiawen
Xiong, Zehui
Niyato, Dusit
Zou, Yuze
Zhang, Y.
Guizani, M.
author_sort Kang, Jiawen
collection NTU
description Federated learning, as a promising machine learning approach, has emerged to leverage a distributed personalized dataset from a number of nodes, for example, mobile devices, to improve performance while simultaneously providing privacy preservation for mobile users. In federated learning, training data is widely distributed and maintained on the mobile devices as workers. A central aggregator updates a global model by collecting local updates from mobile devices using their local training data to train the global model in each iteration. However, unreliable data may be uploaded by the mobile devices (i.e., workers), leading to frauds in tasks of federated learning. The workers may perform unreliable updates intentionally, for example, the data poisoning attack, or unintentionally, for example, low-quality data caused by energy constraints or high-speed mobility. Therefore, finding out trusted and reliable workers in federated learning tasks becomes critical. In this article, the concept of reputation is introduced as a metric. Based on this metric, a reliable worker selection scheme is proposed for federated learning tasks. Consortium blockchain is leveraged as a decentralized approach for achieving efficient reputation management of the workers without repudiation and tampering. By numerical analysis, the proposed approach is demonstrated to improve the reliability of federated learning tasks in mobile networks.
first_indexed 2024-10-01T05:49:41Z
format Journal Article
id ntu-10356/154439
institution Nanyang Technological University
language English
last_indexed 2024-10-01T05:49:41Z
publishDate 2021
record_format dspace
spelling ntu-10356/1544392021-12-22T08:14:25Z Reliable federated learning for mobile networks Kang, Jiawen Xiong, Zehui Niyato, Dusit Zou, Yuze Zhang, Y. Guizani, M. School of Computer Science and Engineering Engineering::Computer science and engineering Mobile Handsets Task Analysis Federated learning, as a promising machine learning approach, has emerged to leverage a distributed personalized dataset from a number of nodes, for example, mobile devices, to improve performance while simultaneously providing privacy preservation for mobile users. In federated learning, training data is widely distributed and maintained on the mobile devices as workers. A central aggregator updates a global model by collecting local updates from mobile devices using their local training data to train the global model in each iteration. However, unreliable data may be uploaded by the mobile devices (i.e., workers), leading to frauds in tasks of federated learning. The workers may perform unreliable updates intentionally, for example, the data poisoning attack, or unintentionally, for example, low-quality data caused by energy constraints or high-speed mobility. Therefore, finding out trusted and reliable workers in federated learning tasks becomes critical. In this article, the concept of reputation is introduced as a metric. Based on this metric, a reliable worker selection scheme is proposed for federated learning tasks. Consortium blockchain is leveraged as a decentralized approach for achieving efficient reputation management of the workers without repudiation and tampering. By numerical analysis, the proposed approach is demonstrated to improve the reliability of federated learning tasks in mobile networks. Agency for Science, Technology and Research (A*STAR) Ministry of Education (MOE) National Research Foundation (NRF) This work was supported in part by Singapore NRF National Satellite of Excellence, Design Science and Technology for Secure Critical Infrastructure NSoE DeST-SCI2019-0007; A*STAR-NTU-SUTD Joint Research Grant Call on Artifi cial Intelligence for the Future of Manufacturing RGANS1906, WASP/NTU M4082187 (4080); Singapore MOE Tier 1 2017-T1-002-007 RG122/17, MOE Tier 2 MOE2014-T2-2-015 ARC4/15, Singapore NRF2015-NRF-ISF001-2277, and Singapore EMA Energy Resilience NRF2017EWT-EP003-041; and the National Natural Science Foundation of China under Grant 61601336. 2021-12-22T08:14:25Z 2021-12-22T08:14:25Z 2020 Journal Article Kang, J., Xiong, Z., Niyato, D., Zou, Y., Zhang, Y. & Guizani, M. (2020). Reliable federated learning for mobile networks. IEEE Wireless Communications, 27(2), 72-80. https://dx.doi.org/10.1109/MWC.001.1900119 1556-6013 https://hdl.handle.net/10356/154439 10.1109/MWC.001.1900119 2-s2.0-85079692164 2 27 72 80 en NSoE DeST-SCI2019-0007 RGANS1906 WASP/NTU M4082187 (4080) 2017-T1-002-007 RG122/17 MOE2014-T2-2-015 ARC4/15 NRF2015-NRF-ISF001-2277 NRF2017EWT-EP003-041 IEEE Wireless Communications © 2020 IEEE. All rights reserved.
spellingShingle Engineering::Computer science and engineering
Mobile Handsets
Task Analysis
Kang, Jiawen
Xiong, Zehui
Niyato, Dusit
Zou, Yuze
Zhang, Y.
Guizani, M.
Reliable federated learning for mobile networks
title Reliable federated learning for mobile networks
title_full Reliable federated learning for mobile networks
title_fullStr Reliable federated learning for mobile networks
title_full_unstemmed Reliable federated learning for mobile networks
title_short Reliable federated learning for mobile networks
title_sort reliable federated learning for mobile networks
topic Engineering::Computer science and engineering
Mobile Handsets
Task Analysis
url https://hdl.handle.net/10356/154439
work_keys_str_mv AT kangjiawen reliablefederatedlearningformobilenetworks
AT xiongzehui reliablefederatedlearningformobilenetworks
AT niyatodusit reliablefederatedlearningformobilenetworks
AT zouyuze reliablefederatedlearningformobilenetworks
AT zhangy reliablefederatedlearningformobilenetworks
AT guizanim reliablefederatedlearningformobilenetworks