Federated Multimedia Recommendation Systems with Privacy Protection

In this big data era, distributed machine learning and global data pooling have become quite critical in practical implementation of any multimedia data-science technique. The emerging federated multimedia recommendation systems (FeMRSs) offer a promising approach to address the need of personalized...

Full description

Saved in:
Bibliographic Details
Published in:IEEE International Symposium on Broadband Multimedia Systems and Broadcasting pp. 1 - 7
Main Authors: Chang, Shih Yu, Wu, Hsiao-Chun, Yan, Kun, Huang, Scott Chih-Hao, Wu, Yiyan
Format: Conference Proceeding
Language:English
Published: IEEE 19.06.2024
Subjects:
collaborative filtering
differential privacy (DP)
Federated multimedia recommendation system (FeMRS)
matrix sketching
personalized dimensionalityreduction algorithm
randomized DP matrix factorization algorithm
ISSN:2155-5052
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this big data era, distributed machine learning and global data pooling have become quite critical in practical implementation of any multimedia data-science technique. The emerging federated multimedia recommendation systems (FeMRSs) offer a promising approach to address the need of personalized recommendations subject to both users' privacy and data security. However, there exists no quantitative method for assessing the discrepancy between the large original rating matrix stored on the server and the dimensionality-reduced rating matrix produced on each client's equipment. Meanwhile, there lacks a systematic means to evaluate the differential privacy (DP), which is a critical security measure in many distributed systems, particularly when sensitive data are processed. In this work, we first introduce a novel personalized dimensionalityreduction algorithm utilizing the matrix sketching technique. This new algorithm effectively control the difference between the original rating matrix on the server and the dimensionality-reduced rating matrix on each client's equipment. Moreover, a randomized DP matrix factorization algorithm is designed to be executed at each client's equipment. The theoretical proof is also carried out to show how much DP can be attained by use of the aforementioned randomized DP matrix factorization algorithm. Finally, extensive numerical studies are presented to evaluate the effectiveness of our proposed novel algorithms using both simulated and real datasets for building the FeMRSs.
AbstractList In this big data era, distributed machine learning and global data pooling have become quite critical in practical implementation of any multimedia data-science technique. The emerging federated multimedia recommendation systems (FeMRSs) offer a promising approach to address the need of personalized recommendations subject to both users' privacy and data security. However, there exists no quantitative method for assessing the discrepancy between the large original rating matrix stored on the server and the dimensionality-reduced rating matrix produced on each client's equipment. Meanwhile, there lacks a systematic means to evaluate the differential privacy (DP), which is a critical security measure in many distributed systems, particularly when sensitive data are processed. In this work, we first introduce a novel personalized dimensionalityreduction algorithm utilizing the matrix sketching technique. This new algorithm effectively control the difference between the original rating matrix on the server and the dimensionality-reduced rating matrix on each client's equipment. Moreover, a randomized DP matrix factorization algorithm is designed to be executed at each client's equipment. The theoretical proof is also carried out to show how much DP can be attained by use of the aforementioned randomized DP matrix factorization algorithm. Finally, extensive numerical studies are presented to evaluate the effectiveness of our proposed novel algorithms using both simulated and real datasets for building the FeMRSs.
Author Wu, Hsiao-Chun
Huang, Scott Chih-Hao
Chang, Shih Yu
Wu, Yiyan
Yan, Kun
Author_xml – sequence: 1
  givenname: Shih Yu
  surname: Chang
  fullname: Chang, Shih Yu
  email: shihyu.chang@sjsu.edu
  organization: San Jose State University,Department of Applied Data Science,San Jose,CA,USA,95192
– sequence: 2
  givenname: Hsiao-Chun
  surname: Wu
  fullname: Wu, Hsiao-Chun
  email: wu@ece.lsu.edu
  organization: Louisiana State University,School of Electrical Engineering and Computer Science,Baton Rouge,LA,USA,70803
– sequence: 3
  givenname: Kun
  surname: Yan
  fullname: Yan, Kun
  email: kyan5702@gmail.com
  organization: Guilin University of Electronic Technology,Guangxi Key Laboratory of Wireless Wideband Communication, and Signal Processing,Guilin,Guangxi,China,541004
– sequence: 4
  givenname: Scott Chih-Hao
  surname: Huang
  fullname: Huang, Scott Chih-Hao
  email: chhuang@ee.nthu.edu.tw
  organization: Guilin University of Electronic Technology,Department of Information and Telecommunication,Guilin,Guangxi,China,541004
– sequence: 5
  givenname: Yiyan
  surname: Wu
  fullname: Wu, Yiyan
  email: yiyan.wu@sympatico.ca
  organization: National Tsinghua University,Department of Electrical Engineering,Hsinchu,Taiwan,300
BookMark eNo1j9FKwzAUhqMoOGffQLAv0Hpy0qTJpRtOhQ3F6fVImlOMrK200dG3t6L-N9_FDx985-yk7Vpi7IpDzjmY68Vmu1Cotc4RsMg5KNACyiOWmNJoIUGoAhUesxlyKTMJEs9YMgzvME0YKUQxY8sVeeptJJ9uPvcxNOSDTZ-p6pqGWm9j6Np0Ow6RmiE9hPiWPvXhy1bjxC5S9fNfsNPa7gdK_jhnr6vbl-V9tn68e1jerLPASxUzBOdrMFQQt047BRWvtas9lh69Ns6DK0BXfoohJ0lJh6pSXisgVbsSxZxd_noDEe0--tDYftz9d4tvuiRP0A
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/BMSB62888.2024.10608307
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350364262
EISSN 2155-5052
EndPage 7
ExternalDocumentID 10608307
Genre orig-research
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i176t-20bdf09e4e1ab8b60c1f8bfd27d2d89bd0b408cd024eb5e65b26c6d860e6fb723
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001285820100031&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:36:35 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-20bdf09e4e1ab8b60c1f8bfd27d2d89bd0b408cd024eb5e65b26c6d860e6fb723
PageCount 7
ParticipantIDs ieee_primary_10608307
PublicationCentury 2000
PublicationDate 2024-June-19
PublicationDateYYYYMMDD 2024-06-19
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-June-19
  day: 19
PublicationDecade 2020
PublicationTitle IEEE International Symposium on Broadband Multimedia Systems and Broadcasting
PublicationTitleAbbrev BMSB
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000395334
Score 2.2732058
Snippet In this big data era, distributed machine learning and global data pooling have become quite critical in practical implementation of any multimedia...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms collaborative filtering
differential privacy (DP)
Federated multimedia recommendation system (FeMRS)
matrix sketching
personalized dimensionalityreduction algorithm
randomized DP matrix factorization algorithm
Title Federated Multimedia Recommendation Systems with Privacy Protection
URI https://ieeexplore.ieee.org/document/10608307
WOSCitedRecordID wos001285820100031&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPOjFV8U3e_C6NdnN5nFtsXixFFTorWSSCfTgVuq24L83SbdVDx68LYEMySQhmdnvm4-QO0OBVday3BZGhwClorkSyucaSmCOy7KsTBKbkKORmkz0uCWrJy4MIibwGfbiZ_qX7-Z2GVNl4YSL8GKI3PFdKcWarLVNqNAyIiV5i-FiVN_3n577UU03IrgK3tv0_qWjkq6R4eE_B3BEut-EvGy8vWqOyQ7WJ-TgRy3BUzIYxrIQ4eXoskSqTZSQLEaXb8HoWjkpa-uTZzH7GgzOVsZ-RsNNAmTVXfI6fHgZPOatQkI-Y1I0YYuD81QjR2ZAgaCWeQXeFdIVTmlwFDhV1oXpI1QoKiiEFU4JisKDLMoz0qnnNZ6TDLgzIVby6LTlISw0wMBQqV3o4I0XF6Qb_TF9XxfBmG5ccflH-xXZj16PqCqmr0mnWSzxhuzZVTP7WNympfsCXpObjA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6ignrxVfHtHrxuTbLZbHJtsVRsS8EKvZVMHtCDW6nbgv_eJN1WPXjwFgIZ8iSZyffNh9C9wkByrUmqqZLeQclxKrhwqYQMiGFFluUqik0Ug4EYj-WwJqtHLoy1NoLPbDMU41--melFCJX5E879iyFwx3dyxihe0bU2IRWcBawkq1FcBMuHVv-lFfR0A4aLsua6_S8llXiRdA7_2YUj1Pim5CXDzWVzjLZseYIOfmQTPEXtTkgM4d-OJom02kgKSYJ_-eaNrrSTkjpDeRLir97gdKn0ZzBcRUhW2UCvncdRu5vWGgnplBS88pscjMPSMksUCOBYEyfAGVoYaoQEg4FhoY0fvoXc8hwo19wIji13UNDsDG2Xs9KeowSYUd5bctZIzbxjqICAwoU0voFTjl-gRpiPyfsqDcZkPRWXf9Tfob3uqN-b9J4Gz1doP6xAwFgReY22q_nC3qBdvaymH_PbuIxfpBie0w
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%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Symposium+on+Broadband+Multimedia+Systems+and+Broadcasting&rft.atitle=Federated+Multimedia+Recommendation+Systems+with+Privacy+Protection&rft.au=Chang%2C+Shih+Yu&rft.au=Wu%2C+Hsiao-Chun&rft.au=Yan%2C+Kun&rft.au=Huang%2C+Scott+Chih-Hao&rft.date=2024-06-19&rft.pub=IEEE&rft.eissn=2155-5052&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FBMSB62888.2024.10608307&rft.externalDocID=10608307