Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching

Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on communications Jg. 73; H. 8; S. 6006 - 6022
Hauptverfasser: Tharakan, Krishnendu S., Dahrouj, Hayssam, Kouzayha, Nour, ElSawy, Hesham, Al-Naffouri, Tareq Y.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.08.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Approximation algorithms
Caching
Communication
Customization
Delays
Distance learning
distributed online learning
Edge computing
Federated learning
federated learning (FL)
Field of view (FoV)
Mobile computing
Multicast algorithms
Real time
Real-time systems
Resource management
Servers
Stochastic processes
Videos
Virtual reality
virtual reality (VR)
Wireless communication
ISSN:0090-6778, 1558-0857
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of <inline-formula> <tex-math notation="LaTeX">\mathcal {O}(1/\sqrt {T}) </tex-math></inline-formula> is obtained for the proposed algorithm, where T is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms.
AbstractList Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of [Formula Omitted] is obtained for the proposed algorithm, where T is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms.
Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of <inline-formula> <tex-math notation="LaTeX">\mathcal {O}(1/\sqrt {T}) </tex-math></inline-formula> is obtained for the proposed algorithm, where T is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms.
Author Al-Naffouri, Tareq Y.
Dahrouj, Hayssam
Kouzayha, Nour
Tharakan, Krishnendu S.
ElSawy, Hesham
Author_xml – sequence: 1
  givenname: Krishnendu S.
  orcidid: 0000-0003-4172-8279
  surname: Tharakan
  fullname: Tharakan, Krishnendu S.
  email: k.tharakan@queensu.ca
  organization: School of Computing, Queen's University, Kingston, ON, Canada
– sequence: 2
  givenname: Hayssam
  orcidid: 0000-0002-0737-6372
  surname: Dahrouj
  fullname: Dahrouj, Hayssam
  email: hayssam.dahrouj@gmail.com
  organization: Department of Electrical Engineering, University of Sharjah, Sharjah, United Arab Emirates
– sequence: 3
  givenname: Nour
  orcidid: 0000-0002-0660-2737
  surname: Kouzayha
  fullname: Kouzayha, Nour
  email: nour.kouzayha@kaust.edu.sa
  organization: Electrical and Computer Engineering Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia
– sequence: 4
  givenname: Hesham
  orcidid: 0000-0003-4201-6126
  surname: ElSawy
  fullname: ElSawy, Hesham
  email: hesham.elsawy@queensu.ca
  organization: School of Computing, Queen's University, Kingston, ON, Canada
– sequence: 5
  givenname: Tareq Y.
  orcidid: 0000-0001-6955-4720
  surname: Al-Naffouri
  fullname: Al-Naffouri, Tareq Y.
  email: tareq.alnaffouri@kaust.edu.sa
  organization: Electrical and Computer Engineering Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST), Thuwal, Kingdom of Saudi Arabia
BookMark eNp9kU1LAzEQhoMoWKt_QDwseN6aj81u4k1Wq0JLRarXJZtMNGWbrcn2UH-9W1tQPHjKEN5nhnnmBB361gNC5wSPCMHyal7OptMRxZSPGGdcFOIADQjnIsWCF4dogLHEaV4U4hidxLjAGGeYsQGaP0GIrVeN-wSTjMFAUF1fTUAF7_xbYtuQlNA060aF5PX5Opn5xnn4CShvktuNV0unk1Lp9_7vFB1Z1UQ4279D9DK-m5cP6WR2_1jeTFJNZd6lPCuwtlYKqUktalnXxtZ1BiY3jBYWtOaEgVR5DpnJwWiQtSJMGkGtJFSyIbrc9V2F9mMNsasW7Tr0y8SK0SznXAqM-xTdpXRoYwxgq1VwSxU2FcHV1l71ba_a2qv29npI_IG061TnWt8F5Zr_0Ysd6gDg16z-EAxz9gXwR4A0
CODEN IECMBT
CitedBy_id crossref_primary_10_1016_j_displa_2025_103210
crossref_primary_10_3390_app15084201
Cites_doi 10.1109/JSTSP.2023.3276595
10.1109/TMC.2024.3365951
10.1109/TCOMM.2018.2850303
10.1109/TIP.2022.3228521
10.1145/3097895.3097901
10.1109/JSAC.2021.3119144
10.1109/TIT.2022.3175900
10.1109/TWC.2022.3229134
10.1090/cbms/107
10.1109/TVT.2022.3212868
10.1109/TWC.2021.3073623
10.1109/LWC.2023.3273318
10.1109/TVCG.2018.2794119
10.1109/TCOMM.2021.3132048
10.1109/TWC.2022.3178618
10.1109/LWC.2019.2926726
10.1109/MCOM.001.1900511
10.1109/TCOMM.2018.2835479
10.1145/3083187.3083210
10.1109/JPROC.2019.2894817
10.1109/TSP.2020.2981904
10.1109/MSP.2020.2975749
10.1109/TMLCN.2024.3388975
10.1109/OJCOMS.2024.3429198
10.1145/3083187.3083219
10.1109/JSAC.2023.3345427
10.1007/978-94-009-2438-3
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/TCOMM.2025.3535878
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
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 Engineering
EISSN 1558-0857
EndPage 6022
ExternalDocumentID 10_1109_TCOMM_2025_3535878
10857305
Genre orig-research
GrantInformation_xml – fundername: King Abdullah University of Science and Technology Research Funding (KRF)
  grantid: ORFS-2023-OFP-5615.2
  funderid: 10.13039/501100004052
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACKIV
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IES
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
ZCA
ZCG
AAYXX
CITATION
7SP
8FD
L7M
ID FETCH-LOGICAL-c296t-5470cff989c1b8b9bbdfbb4ed6d327fecc513e9a66e4d6edce9ba139d82f91293
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001551608400018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0090-6778
IngestDate Sat Nov 01 15:03:53 EDT 2025
Sat Nov 29 07:37:29 EST 2025
Tue Nov 18 21:55:21 EST 2025
Wed Aug 27 07:40:15 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 8
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-c296t-5470cff989c1b8b9bbdfbb4ed6d327fecc513e9a66e4d6edce9ba139d82f91293
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-4172-8279
0000-0002-0737-6372
0000-0002-0660-2737
0000-0001-6955-4720
0000-0003-4201-6126
PQID 3246559800
PQPubID 85472
PageCount 17
ParticipantIDs crossref_citationtrail_10_1109_TCOMM_2025_3535878
proquest_journals_3246559800
ieee_primary_10857305
crossref_primary_10_1109_TCOMM_2025_3535878
PublicationCentury 2000
PublicationDate 2025-08-01
PublicationDateYYYYMMDD 2025-08-01
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-08-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on communications
PublicationTitleAbbrev TCOMM
PublicationYear 2025
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
ref14
ref36
ref31
ref33
ref10
Paria (ref11); 34
ref2
ref17
ref16
ref19
McMahan (ref22); 54
ref18
Anava (ref30)
Bernstein (ref29); 80
Smith (ref25)
Konečný (ref32) 2016
ref24
ref26
ref20
ref21
ref28
Hazan (ref34)
ref27
ref8
ref7
ref9
Karimireddy (ref23); 119
ref4
ref3
(ref1) 2023
ref6
ref5
References_xml – ident: ref17
  doi: 10.1109/JSTSP.2023.3276595
– ident: ref27
  doi: 10.1109/TMC.2024.3365951
– volume-title: Virtual Reality (VR) Market Size and Share Report
  year: 2023
  ident: ref1
– volume: 119
  start-page: 5132
  volume-title: Proc. 37th Int. Conf. Mach. Learn.
  ident: ref23
  article-title: SCAFFOLD: Stochastic controlled averaging for federated learning
– volume: 80
  start-page: 560
  volume-title: Proc. 35th Int. Conf. Mach. Learn.
  ident: ref29
  article-title: SignSGD: Compressed optimisation for non-convex problems
– ident: ref6
  doi: 10.1109/TCOMM.2018.2850303
– start-page: 4424
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref25
  article-title: Federated multitask learning
– ident: ref13
  doi: 10.1109/TIP.2022.3228521
– ident: ref28
  doi: 10.1145/3097895.3097901
– ident: ref16
  doi: 10.1109/JSAC.2021.3119144
– ident: ref9
  doi: 10.1109/TIT.2022.3175900
– ident: ref15
  doi: 10.1109/TWC.2022.3229134
– ident: ref33
  doi: 10.1090/cbms/107
– ident: ref14
  doi: 10.1109/TVT.2022.3212868
– ident: ref5
  doi: 10.1109/TWC.2021.3073623
– ident: ref19
  doi: 10.1109/LWC.2023.3273318
– ident: ref8
  doi: 10.1109/TVCG.2018.2794119
– ident: ref21
  doi: 10.1109/TCOMM.2021.3132048
– ident: ref12
  doi: 10.1109/TWC.2022.3178618
– ident: ref4
  doi: 10.1109/LWC.2019.2926726
– start-page: 172
  volume-title: Proc. Conf. Learn. Theory
  ident: ref30
  article-title: Online learning for time series prediction
– ident: ref3
  doi: 10.1109/MCOM.001.1900511
– volume: 54
  start-page: 1273
  volume-title: Proc. 20th Int. Conf. Artif. Intell. Statist.
  ident: ref22
  article-title: Communication-efficient learning of deep networks from decentralized data
– ident: ref10
  doi: 10.1109/TCOMM.2018.2835479
– ident: ref36
  doi: 10.1145/3083187.3083210
– ident: ref7
  doi: 10.1109/JPROC.2019.2894817
– year: 2016
  ident: ref32
  article-title: Federated learning: Strategies for improving communication efficiency
  publication-title: arxiv.1610.05492
– ident: ref20
  doi: 10.1109/TSP.2020.2981904
– ident: ref24
  doi: 10.1109/MSP.2020.2975749
– ident: ref31
  doi: 10.1109/TMLCN.2024.3388975
– start-page: 1433
  volume-title: Proc. 35th Int. Conf. Mach. Learn.
  ident: ref34
  article-title: Efficient regret minimization in non-convex games
– ident: ref18
  doi: 10.1109/OJCOMS.2024.3429198
– ident: ref35
  doi: 10.1145/3083187.3083219
– volume: 34
  start-page: 4435
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref11
  article-title: Leadcache: Regret-optimal caching in networks
– ident: ref2
  doi: 10.1109/JSAC.2023.3345427
– ident: ref26
  doi: 10.1007/978-94-009-2438-3
SSID ssj0004033
Score 2.4959137
Snippet Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time....
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 6006
SubjectTerms Algorithms
Approximation algorithms
Caching
Communication
Customization
Delays
Distance learning
distributed online learning
Edge computing
Federated learning
federated learning (FL)
Field of view (FoV)
Mobile computing
Multicast algorithms
Real time
Real-time systems
Resource management
Servers
Stochastic processes
Videos
Virtual reality
virtual reality (VR)
Wireless communication
Title Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching
URI https://ieeexplore.ieee.org/document/10857305
https://www.proquest.com/docview/3246559800
Volume 73
WOSCitedRecordID wos001551608400018&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: 1558-0857
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004033
  issn: 0090-6778
  databaseCode: RIE
  dateStart: 19720101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5ueNCDPydOp-TgTbqlTds03qQ6vGwOmbJbSZNUhNHJfnjwrzcvTd1AFLyUHpJS3pc232u_9z2ErgjjRNE4NEmONAlK5CtPUKo9rgXYfwmdCGGbTbDhMJlM-MgVq9taGK21FZ_pLpzaf_lqJlfwqawHSnmzIqMGajDGqmKtdREkoc5yEvTsLKkrZAjvjdPHwcDkgkHUpRGNEuiptrEL2bYqP97FdoPp7__z1g7QnmOS-LaC_hBt6fII7W74Cx6j8aim2p9a4T74RhhqqbAzVX3FhrHiVE-noEXFL083uHIeXQ8QpcJ3VdN6nFa6yxZ67t-P0wfPtVHwZMDjpReFjMii4AmXfp7kPM9VkeehVrGiASsMhpFPNRdxrEMVgyqU58IQQ5UEBQc6cIKa5azUpwjHVEjNfHMQJFScJKEvwS2nUBEUM_A28uuwZtJ5jEOri2lmcw3CMwtFBlBkDoo2uv6e8145bPw5ugXB3xhZxb2NOjV8mXsKF5khizEY0BNy9su0c7QDV68UfR3UXM5X-gJty4_l22J-aRfYFwlazTE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8QwEB38AvXg54rrZw7epJo2Tdt4k9Vlxd1VpIq3kiapCEsVd9eDv95M2tUFUfBSekhomZc2b9o3bwCOaCyoZlFokxxlExTua08yZjxhJNp_SZNI6ZpNxP1-8vgobutidVcLY4xx4jNzgqfuX75-UWP8VHaKSnm7IvkszPMwDPyqXOu7DJKy2nQSFe1xMqmRoeI0bd30ejYbDPgJ44wn2FVtah9yjVV-vI3dFtNe_efNrcFKzSXJeQX-OsyYcgOWpxwGNyG9nZDtD6NJG50jLLnUpLZVfSKWs5KWGQxQjUoe7s5I5T36PUCWmlxUbetJq1JeNuC-fZm2Ol7dSMFTgYhGHg9jqopCJEL5eZKLPNdFnodGR5oFcWFR5D4zQkaRCXWEulCRS0sNdRIUAgnBFsyVL6XZBhIxqUzs24OkoRY0CX2FfjmF5ljOIJrgT8KaqdplHJtdDDKXbVCROSgyhCKroWjC8dec18pj48_RDQz-1Mgq7k3Ym8CX1c_hMLN0MUILekp3fpl2CIudtNfNulf9611YwitV-r49mBu9jc0-LKj30fPw7cAttk_fbdB4
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=Personalized+Federated+Learning+for+Cellular+VR%3A+Online+Learning+and+Dynamic+Caching&rft.jtitle=IEEE+transactions+on+communications&rft.au=Tharakan%2C+Krishnendu+S.&rft.au=Dahrouj%2C+Hayssam&rft.au=Kouzayha%2C+Nour&rft.au=ElSawy%2C+Hesham&rft.date=2025-08-01&rft.pub=IEEE&rft.issn=0090-6778&rft.volume=73&rft.issue=8&rft.spage=6006&rft.epage=6022&rft_id=info:doi/10.1109%2FTCOMM.2025.3535878&rft.externalDocID=10857305
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0090-6778&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0090-6778&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0090-6778&client=summon