CAST: Cluster-Driven Truthful Crowdfunding Mechanism for Shared AI Service Deployment

The rapid growth of AI models has substantially increased the cost of deploying services on servers. Fortunately, their generality enables them to serve multiple clients with similar tasks, presenting opportunities to optimize service deployment and maximize social utility by service sharing. Existi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on services computing pp. 1 - 14
Main Authors: Liu, Hongze, Wang, Mengru, Liu, Junzhe, Yuan, Shijing, Lou, Jiong, Wu, Chentao, Li, Jie
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
Artificial intelligence
Auction Theory
Biological system modeling
Cluster Algorithm
Clustering algorithms
Computational modeling
Costs
Federated learning
Mechanism Design
Privacy
Scalability
Servers
Service Deployment
Virtual machines
ISSN:1939-1374, 2372-0204
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The rapid growth of AI models has substantially increased the cost of deploying services on servers. Fortunately, their generality enables them to serve multiple clients with similar tasks, presenting opportunities to optimize service deployment and maximize social utility by service sharing. Existing approaches for shared service deployment often rely on centralized algorithms that overlook privacy concerns and selfish behavior, leading to untruthful and suboptimal outcomes in distributed networks. While Vickrey-Clarke-Groves (VCG) mechanisms are widely used to ensure truthfulness, their adaptation to shared service deployment faces challenges related to individual rationality and scalability. To tackle these issues, we propose a novel auction mechanism based on the VCG framework, enhanced with targeted clustering algorithms. Theoretical analysis demonstrates that the clustering algorithms with controllable radius bound can mitigate the limitations of naive VCG. To preserve privacy, we further design a Bayesian, utility-likelihood clustering scheme that requires clients to reveal only utility values rather than individual details. By combining VCG with adaptive clustering, our mechanism achieves guarantees in truthfulness, economic properties, and performance. Experimental evaluations, including a case study in Non-IID federated learning, validate the effectiveness of the proposed approach, showing significant improvements in overall utility and reduction in negative individual utility instances by over 90%.
AbstractList The rapid growth of AI models has substantially increased the cost of deploying services on servers. Fortunately, their generality enables them to serve multiple clients with similar tasks, presenting opportunities to optimize service deployment and maximize social utility by service sharing. Existing approaches for shared service deployment often rely on centralized algorithms that overlook privacy concerns and selfish behavior, leading to untruthful and suboptimal outcomes in distributed networks. While Vickrey-Clarke-Groves (VCG) mechanisms are widely used to ensure truthfulness, their adaptation to shared service deployment faces challenges related to individual rationality and scalability. To tackle these issues, we propose a novel auction mechanism based on the VCG framework, enhanced with targeted clustering algorithms. Theoretical analysis demonstrates that the clustering algorithms with controllable radius bound can mitigate the limitations of naive VCG. To preserve privacy, we further design a Bayesian, utility-likelihood clustering scheme that requires clients to reveal only utility values rather than individual details. By combining VCG with adaptive clustering, our mechanism achieves guarantees in truthfulness, economic properties, and performance. Experimental evaluations, including a case study in Non-IID federated learning, validate the effectiveness of the proposed approach, showing significant improvements in overall utility and reduction in negative individual utility instances by over 90%.
Author Liu, Junzhe
Liu, Hongze
Lou, Jiong
Li, Jie
Wang, Mengru
Yuan, Shijing
Wu, Chentao
Author_xml – sequence: 1
  givenname: Hongze
  surname: Liu
  fullname: Liu, Hongze
  email: eniordriver233@sjtu.edu.cn
  organization: Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
– sequence: 2
  givenname: Mengru
  surname: Wang
  fullname: Wang, Mengru
  email: dreamfish@sjtu.edu.cn
  organization: Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
– sequence: 3
  givenname: Junzhe
  surname: Liu
  fullname: Liu, Junzhe
  email: jz_liu@sjtu.edu.cn
  organization: School of Mathematical Sciences, Shanghai Jiao Tong University, China
– sequence: 4
  givenname: Shijing
  surname: Yuan
  fullname: Yuan, Shijing
  email: 2019ysj@sjtu.edu.cn
  organization: Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
– sequence: 5
  givenname: Jiong
  surname: Lou
  fullname: Lou, Jiong
  email: lj1994@sjtu.edu.cn
  organization: Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
– sequence: 6
  givenname: Chentao
  surname: Wu
  fullname: Wu, Chentao
  email: wuct@sjtu.edu.cn
  organization: Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
– sequence: 7
  givenname: Jie
  surname: Li
  fullname: Li, Jie
  email: lijiecs@sjtu.edu.cn
  organization: MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, China
BookMark eNpFkL1uwjAURq2KSgXavUMHv0DotR3HcTcU-oNE1SFhjox9XVKFBDkJFW9fEEidvuWcbzgTMmraBgl5ZDBjDPRzkWczDlzORMLSVPMbMuZC8Qg4xCMyZlroiAkV35FJ1_0AJPxEjck6m-fFC83qoesxRItQHbChRRj6rR9qmoX21_mhcVXzTT_Rbk1TdTvq20DzrQno6HxJcwyHyiJd4L5ujzts-nty603d4cN1p2T99lpkH9Hq632ZzVeRZSLuIwlmA9IwzZXTHpTiHryMOajEeUwTB1YzHXvgDhD0xtrUbZQ0CcSpFFyJKYHLrw1t1wX05T5UOxOOJYPynKU8ZSnPWcprlpPydFEqRPzHGdNSaSX-AFhmX74
CODEN ITSCAD
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TSC.2025.3618892
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL) (UW System Shared)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2372-0204
EndPage 14
ExternalDocumentID 10_1109_TSC_2025_3618892
11195797
Genre orig-research
GroupedDBID 0R~
29I
5VS
6IK
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RZB
4.4
AAYXX
AETIX
AGSQL
CITATION
M43
RNI
ID FETCH-LOGICAL-c134t-50ab05a1927d9f0772f0f542076dfe86d0c9194f02d0e09bcc8db75a604853273
IEDL.DBID RIE
ISSN 1939-1374
IngestDate Sat Nov 29 07:17:17 EST 2025
Wed Oct 15 14:20:43 EDT 2025
IsPeerReviewed true
IsScholarly true
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-c134t-50ab05a1927d9f0772f0f542076dfe86d0c9194f02d0e09bcc8db75a604853273
PageCount 14
ParticipantIDs crossref_primary_10_1109_TSC_2025_3618892
ieee_primary_11195797
PublicationCentury 2000
PublicationDate 2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025-00-00
PublicationDecade 2020
PublicationTitle IEEE transactions on services computing
PublicationTitleAbbrev TSC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0062889
Score 2.3702312
Snippet The rapid growth of AI models has substantially increased the cost of deploying services on servers. Fortunately, their generality enables them to serve...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms Artificial intelligence
Auction Theory
Biological system modeling
Cluster Algorithm
Clustering algorithms
Computational modeling
Costs
Federated learning
Mechanism Design
Privacy
Scalability
Servers
Service Deployment
Virtual machines
Title CAST: Cluster-Driven Truthful Crowdfunding Mechanism for Shared AI Service Deployment
URI https://ieeexplore.ieee.org/document/11195797
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared)
  customDbUrl:
  eissn: 2372-0204
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0062889
  issn: 1939-1374
  databaseCode: RIE
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27TsMwFLVoxQADzyLKSx5YGNI6D7_YqkAFElRIbaVuURzbolJpUZrw_fgmqSgDA1uUOJJ1rNx7rp17DkK3NAI7cqY8FllXoMjQeIpHqcc1EZapNNWqUtd_4aORmM3kW9OsXvXCGGOqn89MDy6rs3y9ykrYKuv7oE_GJW-hFuesbtbahF2wzZWbc0gi-5Nx7Kq_gPZC5rsnwa-8s2WkUuWR4eE_Z3CEDhrCiAf1Ch-jHbM8QftbMoKnaBoPxpN7HC9KUD3wHnKIYHiSl8W7LRc4dpW2dvkLshR-NdDqO19_YMdWMcg1G40Hz7iJGfjBgAMwzKKDpsPHSfzkNXYJXuaHUeFRkipCU0fZuJaWONpsiaVRQDjT1gimSSZ9GVkSaGKIVFkmtOI0Ze4jpqGjMWeovVwtzTnCQgDxCZRQoYgy6oZxpowvtLbc2jTtorsNmMlnrYqRVNUEkYkDPgHgkwb4LuoAjj_jGggv_rh_ifbg9Xqb4wq1i7w012g3-yrm6_ymWvNvKGSrxg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4UTdSDPzHizx68eBh0P9t6I0MCEYgJI-G2rGsbSRDM2Pz77Rsj4sGDt2VrluZr9t732r3vQ-jR98COPBBW4GlToHBXWYJ6iUUlYToQSSJFqa4_oKMRm075W9WsXvbCKKXKn89UEy7Ls3y5TAvYKmvZoE9GOd1Fe2CdVbVrbQIvGOfyzUkk4a1oHJr6z_GbbmCbJ86vzLNlpVJmku7JP-dwio4ryojb6zU-QztqcY6OtoQEL9AkbI-jZxzOC9A9sDoZxDAcZUX-ros5Dk2tLU0GgzyFhwqafWerD2z4KgbBZiVxu4-rqIE7CjyAYRZ1NOm-RGHPqgwTrNR2vdzySSKInxjSRiXXxBBnTbTvOYQGUisWSJJym3uaOJIowkWaMimonwTmM_ZdQ2QuUW2xXKgrhBkD6uMIJlzmpb4ZRgOhbCalplonSQM9bcCMP9e6GHFZTxAeG-BjAD6ugG-gOuD4M66C8PqP-w_ooBcNB_GgP3q9QYfwqvWmxy2q5Vmh7tB--pXPVtl9uf7fSravDw
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=CAST%3A+Cluster-Driven+Truthful+Crowdfunding+Mechanism+for+Shared+AI+Service+Deployment&rft.jtitle=IEEE+transactions+on+services+computing&rft.au=Liu%2C+Hongze&rft.au=Wang%2C+Mengru&rft.au=Liu%2C+Junzhe&rft.au=Yuan%2C+Shijing&rft.date=2025&rft.issn=1939-1374&rft.eissn=2372-0204&rft.spage=1&rft.epage=14&rft_id=info:doi/10.1109%2FTSC.2025.3618892&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSC_2025_3618892
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1939-1374&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1939-1374&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1939-1374&client=summon