Reputation-Aware Federated Learning Client Selection Based on Stochastic Integer Programming

Federated Learning(FL) has attracted wide research interest due to its potential in building machine learning models while preserving users' data privacy. However, due to the distributive nature of FL, it is vulnerable to misbehavior from participating worker nodes. Thus, it is important to sel...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on big data Vol. 10; no. 6; pp. 953 - 964
Main Authors:	Tan, Xavier, Ng, Wei Chong, Lim, Wei Yang Bryan, Xiong, Zehui, Niyato, Dusit, Yu, Han
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01.12.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Biological system modeling client selection Clients Computational modeling Costs Data models Federated learning Integer programming Machine learning reputation stochastic integer programming Stochastic processes Training Uncertainty
ISSN:	2332-7790, 2372-2096
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Federated Learning(FL) has attracted wide research interest due to its potential in building machine learning models while preserving users' data privacy. However, due to the distributive nature of FL, it is vulnerable to misbehavior from participating worker nodes. Thus, it is important to select clients to participate in FL. Recent studies on FL client selection focus on the perspective of improving model training efficiency and performance, without holistically considering potential misbehavior and the cost of hiring. To bridge this gap, we propose a first-of-its-kind reputation-aware S tochastic integer programming-based FL C lient S election method (SCS). It can optimally select and compensate clients with different reputation profiles. Extensive experiments show that SCS achieves the most advantageous performance-cost trade-off compared to other existing state-of-the-art approaches.
AbstractList	Federated Learning(FL) has attracted wide research interest due to its potential in building machine learning models while preserving users' data privacy. However, due to the distributive nature of FL, it is vulnerable to misbehavior from participating worker nodes. Thus, it is important to select clients to participate in FL. Recent studies on FL client selection focus on the perspective of improving model training efficiency and performance, without holistically considering potential misbehavior and the cost of hiring. To bridge this gap, we propose a first-of-its-kind reputation-aware S tochastic integer programming-based FL C lient S election method (SCS). It can optimally select and compensate clients with different reputation profiles. Extensive experiments show that SCS achieves the most advantageous performance-cost trade-off compared to other existing state-of-the-art approaches.
Author	Yu, Han Xiong, Zehui Ng, Wei Chong Lim, Wei Yang Bryan Tan, Xavier Niyato, Dusit
Author_xml	– sequence: 1 givenname: Xavier orcidid: 0000-0001-9873-0463 surname: Tan fullname: Tan, Xavier email: XAVIER002@e.ntu.edu.sg organization: Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University, Singapore – sequence: 2 givenname: Wei Chong orcidid: 0000-0002-8906-5825 surname: Ng fullname: Ng, Wei Chong email: weichong001@e.ntu.edu.sg organization: Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University, Singapore – sequence: 3 givenname: Wei Yang Bryan orcidid: 0000-0003-2150-5561 surname: Lim fullname: Lim, Wei Yang Bryan email: limw0201@e.ntu.edu.sg organization: Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University, Singapore – sequence: 4 givenname: Zehui orcidid: 0000-0002-4440-941X surname: Xiong fullname: Xiong, Zehui email: ZXIONG002@e.ntu.edu.sg organization: Singapore University of Technology and Design, Singapore – sequence: 5 givenname: Dusit orcidid: 0000-0002-7442-7416 surname: Niyato fullname: Niyato, Dusit email: dniyato@ntu.edu.sg organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore – sequence: 6 givenname: Han orcidid: 0000-0001-6893-8650 surname: Yu fullname: Yu, Han email: han.yu@ntu.edu.sg organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore
BookMark	eNqFkVFLwzAQx4NMcM59gr0UfO5MLmlqHrvpdDBQ3HwTSppeZseWzjRD_Pa2VHzwxac7uP_vDn53SQaudkjIhNEpY1TdbGZ32SabAgWYcqYY53BGhsBTiIEqOeh6DnGaKnpBxk2zo5QySSlXMCRvL3g8BR2q2sXZp_YYLbBErwOW0Qq1d5XbRvN9hS5Ea9yj6ZLRTDftvG3WoTbvugmViZYu4BZ99OzrrdeHQwtekXOr9w2Of-qIvC7uN_PHePX0sJxnq9iASkMMqRRClMoIbplVoIS0rACNgIlkZcFoqSwHsFInQksUujBaFYYqsNomko_Idb_36OuPEzYh39Un79qTOWeQplJRwdoU71PG103j0eZHXx20_8oZzTuTeW8y70zmPyZbSv2hTNX7Cl5X-3_YSc9WiPh7Td1ySNqXfANV2IOs
CODEN	ITBDAX
CitedBy_id	crossref_primary_10_1007_s11831_023_10011_4 crossref_primary_10_1109_JIOT_2023_3265564 crossref_primary_10_3390_s23167235
Cites_doi	10.1561/9781680837896 10.1007/978-3-030-63076-8_9 10.1109/tnet.2023.3312208 10.1109/INFOCOM.2019.8737464 10.1109/tpds.2023.3240767 10.1109/5.726791 10.1145/3298981 10.1145/3375627.3375840 10.1109/MWC.001.1900119 10.1109/CAMAD50429.2020.9209263 10.1109/TNNLS.2019.2919699 10.1109/MIS.2020.2987774 10.1109/WCNC.2018.8377035 10.1109/APSCC.2009.5394134 10.1109/jiot.2022.3161943 10.1109/JIOT.2019.2956615 10.1109/JSAC.2020.3041404 10.1002/9780470400531.eorms0092 10.1109/ICC.2019.8761315 10.1109/MILCOM52596.2021.9653139 10.23919/WiOpt52861.2021.9589776 10.1109/tnnls.2022.3216981 10.1109/MSP.2020.2975749 10.1109/AIEEE.2018.8592253 10.1145/3442381.3449888 10.1038/s41598-016-0011-6 10.1007/s11081-019-09471-0 10.9781/ijimai.2016.415
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TBDATA.2022.3191332
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2372-2096
EndPage	964
ExternalDocumentID	10_1109_TBDATA_2022_3191332 9832523
Genre	orig-research
GrantInformation_xml	– fundername: Nanyang Technological University; Nanyang Technological University, Singapore funderid: 10.13039/501100001475 – fundername: RIE 2020 Advanced Manufacturing and Engineering grantid: A20G8b0102 – fundername: Nanyang Assistant Professorship – fundername: Alibaba Group – fundername: Joint NTU-WeBank Research Centre on Fintech – fundername: Future Communications Research & Development Programme grantid: FCP-NTU-RG-2021-014 – fundername: National Research Foundation Singapore; National Research Foundation, Singapore funderid: 10.13039/501100001381 – fundername: AI Singapore Programme AISG grantid: AISG2-RP-2020-019 – fundername: Alibaba Innovative Research – fundername: Alibaba-NTU Singapore Joint Research Institute
GroupedDBID	0R~ 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IEDLZ IFIPE IPLJI JAVBF M43 O9- OCL RIA RIE AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c297t-276444d9c43f1f92946f1b2ae2e561db10d9f322f6a54a6e4abca9bc092faf563
IEDL.DBID	RIE
ISICitedReferencesCount	9
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001354646300010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2332-7790
IngestDate	Mon Jun 30 12:59:15 EDT 2025 Sat Nov 29 05:31:05 EST 2025 Tue Nov 18 22:38:30 EST 2025 Wed Aug 27 03:06:37 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c297t-276444d9c43f1f92946f1b2ae2e561db10d9f322f6a54a6e4abca9bc092faf563
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6893-8650 0000-0002-4440-941X 0000-0001-9873-0463 0000-0002-8906-5825 0000-0003-2150-5561 0000-0002-7442-7416
PQID	3127769041
PQPubID	4437220
PageCount	12
ParticipantIDs	ieee_primary_9832523 crossref_primary_10_1109_TBDATA_2022_3191332 proquest_journals_3127769041 crossref_citationtrail_10_1109_TBDATA_2022_3191332
PublicationCentury	2000
PublicationDate	2024-12-01
PublicationDateYYYYMMDD	2024-12-01
PublicationDate_xml	– month: 12 year: 2024 text: 2024-12-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE transactions on big data
PublicationTitleAbbrev	TBData
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref15 ref37 ref14 ref31 ref30 ref11 ref33 ref32 ref2 ref1 ref17 ref16 Fung (ref25) Xu (ref10) 2020 Nguyen (ref26) 2021 ref23 McMahan (ref24) Wang (ref18) 2014 ref20 O’Shea (ref34) 2015 ref22 ref21 Sun (ref3) 2019 ref28 ref27 ref29 ref8 ref7 Xiao (ref36) 2017 ref9 ref4 ref6 ref5 Gul (ref19) 2012
References_xml	– ident: ref2 doi: 10.1561/9781680837896 – ident: ref16 doi: 10.1007/978-3-030-63076-8_9 – start-page: 301 volume-title: Proc. 23rd Int. Symp. Res. Attacks, Intrusions Defenses ident: ref25 article-title: The limitations of federated learning in sybil settings – volume-title: Stochastic Integer Program.: DeComp. Methods Ind. Appl. year: 2014 ident: ref18 – ident: ref28 doi: 10.1109/tnet.2023.3312208 – ident: ref32 doi: 10.1109/INFOCOM.2019.8737464 – ident: ref13 doi: 10.1109/tpds.2023.3240767 – year: 2019 ident: ref3 article-title: Can you really backdoor federated learning? – ident: ref33 doi: 10.1109/5.726791 – ident: ref1 doi: 10.1145/3298981 – ident: ref5 doi: 10.1145/3375627.3375840 – ident: ref8 doi: 10.1109/MWC.001.1900119 – ident: ref17 doi: 10.1109/CAMAD50429.2020.9209263 – ident: ref23 doi: 10.1109/TNNLS.2019.2919699 – ident: ref6 doi: 10.1109/MIS.2020.2987774 – ident: ref20 doi: 10.1109/WCNC.2018.8377035 – ident: ref35 doi: 10.1109/APSCC.2009.5394134 – ident: ref12 doi: 10.1109/jiot.2022.3161943 – year: 2017 ident: ref36 article-title: Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms – ident: ref31 doi: 10.1109/JIOT.2019.2956615 – ident: ref29 doi: 10.1109/JSAC.2020.3041404 – ident: ref22 doi: 10.1002/9780470400531.eorms0092 – year: 2012 ident: ref19 article-title: A multi-stage stochastic integer programming model for surgery planning publication-title: Michigan Eng. – year: 2015 ident: ref34 article-title: An introduction to convolutional neural networks – ident: ref4 doi: 10.1109/ICC.2019.8761315 – ident: ref30 doi: 10.1109/MILCOM52596.2021.9653139 – ident: ref14 doi: 10.23919/WiOpt52861.2021.9589776 – year: 2020 ident: ref10 article-title: A reputation mechanism is all you need: Collaborative fairness and adversarial robustness in federated learning – ident: ref27 doi: 10.1109/tnnls.2022.3216981 – ident: ref7 doi: 10.1109/MSP.2020.2975749 – ident: ref15 doi: 10.1109/AIEEE.2018.8592253 – year: 2021 ident: ref26 article-title: FLGUARD: Secure and private federated learning – ident: ref9 doi: 10.1145/3442381.3449888 – ident: ref11 doi: 10.1038/s41598-016-0011-6 – ident: ref21 doi: 10.1007/s11081-019-09471-0 – ident: ref37 doi: 10.9781/ijimai.2016.415 – start-page: 1273 volume-title: Proc. 20th Int. Conf. Artif. Intell. Statist. ident: ref24 article-title: Communication-efficient learning of deep networks from decentralized data
SSID	ssj0001600392
Score	2.3648648
Snippet	Federated Learning(FL) has attracted wide research interest due to its potential in building machine learning models while preserving users' data privacy.... Federated Learning(FL) has attracted wide research interest due to its potential in building machine learning models while preserving users’ data privacy....
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	953
SubjectTerms	Biological system modeling client selection Clients Computational modeling Costs Data models Federated learning Integer programming Machine learning reputation stochastic integer programming Stochastic processes Training Uncertainty
Title	Reputation-Aware Federated Learning Client Selection Based on Stochastic Integer Programming
URI	https://ieeexplore.ieee.org/document/9832523 https://www.proquest.com/docview/3127769041
Volume	10
WOSCitedRecordID	wos001354646300010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2372-2096 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001600392 issn: 2332-7790 databaseCode: RIE dateStart: 20150101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB60ePBifWK1Sg4eXc1ms9nNsVWLp1JoBQ_Cks1DBW2lD_37TnbTiiiCtxwyYdlvknyTZL4BONM6caXX03ZS84gzmkVKpDpKtc41l9zgwlwVm8j6_fz-Xg7W4HyVC2OtrR6f2QvfrO7yzUQv_FHZpUT3w8BpHdazTNS5Wl_nKcKnmbIgLBRTeTnqXndGHQwBGcPIVGIwxr5tPlU1lR9LcLWv9Jr_-6Jt2Ar8kXRqwHdgzY53obmszUDCVN2DB2TWi_qaPep8qKklPS8bgczSkKCp-kiuXnw2JBlWtXCwJ-ninmYINobziX5SXsOZ-DPDRxx6UL_kekXDfbjr3YyubqNQSSHSTGbziGVIe7hBOBIXO2REXLi4ZMoyi_zJlDE10uHUdkKlXAnLVamVLDWVzCmXiuQAGuPJ2B4CMTpBziFzSWnJpXF5nqo8F05oa5xLaQvY8hcXOsiM-2oXL0UVblBZ1LgUHpci4NKC85XRW62y8Xf3PQ_FqmtAoQXtJZZFmIkzNGHoLJLy-Oh3q2PYxLF5_USlDY35dGFPYEO_z59n09PKyT4BOefRFA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFH5oFfTiLtY1B4-OZtJMZnKsS1HUIljBgzBksqigrXTRv-_LTFoRRfCWQ14yzJfle0ne9wD2tW64wutpO6l5xBlNIyUSHSVaZ5pLbnBhLpNNpO12dn8vb6bgYBILY60tH5_ZQ18s7_JNT4_8UdmRxOGHjtM0zCQcm62itb5OVIQPNGVBWiim8qhzfNrsNNEJZAx9U4nuGPu2_ZT5VH4swuXO0lr83zctwUJgkKRZQb4MU7a7Aovj7AwkTNZVeEBuPaou2qPmh-pb0vLCEcgtDQmqqo_k5MXHQ5LbMhsO1iTHuKsZgoXbYU8_Ka_iTPyp4SM2fVO95XpFwzW4a511Ts6jkEsh0kymw4ilSHy4QUAaLnbIibhwccGUZRYZlCliaqTDye2ESrgSlqtCK1loKplTLhGNdah1e127AcToBrIOmUlKCy6Ny7JEZZlwQlvjXELrwMa_ONdBaNznu3jJS4eDyrzCJfe45AGXOhxMjN4qnY2_q696KCZVAwp12B5jmYe5OEATlqZCUh5v_m61B3Pnneur_OqifbkF89gPrx6sbENt2B_ZHZjV78PnQX-3HHCfQanUWw
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Reputation-Aware+Federated+Learning+Client+Selection+Based+on+Stochastic+Integer+Programming&rft.jtitle=IEEE+transactions+on+big+data&rft.au=Tan%2C+Xavier&rft.au=Ng%2C+Wei+Chong&rft.au=Lim%2C+Wei+Yang+Bryan&rft.au=Xiong%2C+Zehui&rft.date=2024-12-01&rft.pub=IEEE&rft.eissn=2372-2096&rft.volume=10&rft.issue=6&rft.spage=953&rft.epage=964&rft_id=info:doi/10.1109%2FTBDATA.2022.3191332&rft.externalDocID=9832523
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2332-7790&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2332-7790&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2332-7790&client=summon