Hermes: Fast Semi-Asynchronous Federated Learning in LEO Constellations

Recent advances in space technology have prompted the emergence of numerous Low Earth Orbit (LEO) satellites, producing mega-constellations that can pro-vide global network coverage and collect massive distributed data, bringing new opportunities for intelligence applications to remote areas. To ach...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE Wireless Communications and Networking Conference : [proceedings] : WCNC s. 1 - 6
Hlavní autori: Chen, Yan, Liu, Jun, Zhao, Jiejie, Jiang, Guanjun, Wang, Haiquan, Du, Bowen
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 21.04.2024
Predmet:
ISSN:1558-2612
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Recent advances in space technology have prompted the emergence of numerous Low Earth Orbit (LEO) satellites, producing mega-constellations that can pro-vide global network coverage and collect massive distributed data, bringing new opportunities for intelligence applications to remote areas. To achieve such goals, Federated Learning (FL) is a promising solution to train the global model over LEO satellites and ground station networks while reducing the high communication cost caused by data exchanging. However, the widely used synchronous FL may face intol-erable waiting time due to the intermittent connectivity. In addition, existing asynchronous FL suffers from model staleness attributed to asynchronous training, which may decrease the performance of the global model. To this end, we propose a novel semi-asynchronous federated learning frame-work in LEO constellations, namely Hermes, that includes a latency-aware model delivery mechanism and an adaptive semi-asynchronous aggregation algorithm to improve the convergence rate and generality of the global model. Our simulation results show that Hermes outperforms existing LEO-based FL methods across various constellation scales, achieving higher model accuracy with average speedups of 3.29x and 7.26x for MNIST and EMNIST, respectively.
AbstractList Recent advances in space technology have prompted the emergence of numerous Low Earth Orbit (LEO) satellites, producing mega-constellations that can pro-vide global network coverage and collect massive distributed data, bringing new opportunities for intelligence applications to remote areas. To achieve such goals, Federated Learning (FL) is a promising solution to train the global model over LEO satellites and ground station networks while reducing the high communication cost caused by data exchanging. However, the widely used synchronous FL may face intol-erable waiting time due to the intermittent connectivity. In addition, existing asynchronous FL suffers from model staleness attributed to asynchronous training, which may decrease the performance of the global model. To this end, we propose a novel semi-asynchronous federated learning frame-work in LEO constellations, namely Hermes, that includes a latency-aware model delivery mechanism and an adaptive semi-asynchronous aggregation algorithm to improve the convergence rate and generality of the global model. Our simulation results show that Hermes outperforms existing LEO-based FL methods across various constellation scales, achieving higher model accuracy with average speedups of 3.29x and 7.26x for MNIST and EMNIST, respectively.
Author Du, Bowen
Zhao, Jiejie
Chen, Yan
Liu, Jun
Jiang, Guanjun
Wang, Haiquan
Author_xml – sequence: 1
  givenname: Yan
  surname: Chen
  fullname: Chen, Yan
  email: juneliu@tsinghua.edu.cn
  organization: School of Software, Beihang University,Beijing,China,100191
– sequence: 2
  givenname: Jun
  surname: Liu
  fullname: Liu, Jun
  email: zhaojiejie@zgclab.edu.cn
  organization: Institute for Network Sciences and Cyberspace, Tsinghua University,Beijing,China,100084
– sequence: 3
  givenname: Jiejie
  surname: Zhao
  fullname: Zhao, Jiejie
  email: chenyan2022@buaa.edu.cn
  organization: Zhongguancun Laboratory
– sequence: 4
  givenname: Guanjun
  surname: Jiang
  fullname: Jiang, Guanjun
  email: whq@buaa.edu.cn
  organization: School of Software, Beihang University,Beijing,China,100191
– sequence: 5
  givenname: Haiquan
  surname: Wang
  fullname: Wang, Haiquan
  email: 1824055481@buaa.edu.cn
  organization: School of Software, Beihang University,Beijing,China,100191
– sequence: 6
  givenname: Bowen
  surname: Du
  fullname: Du, Bowen
  email: dubowen@buaa.edu.cn
  organization: Zhongguancun Laboratory
BookMark eNo1j81Kw0AYAFdRsK19A8F9gcRvf7PxVkLTCsEeVDyWze4XXUk2ko2Hvr2Cepo5DcySXMQxIiG3DHLGoLx7rR4rVXANOQcucwaqYEyWZ2RdFqURCgQIZfg5WTClTMY141dkmdIHAAcl5YLs9jgNmO5pbdNMn3AI2Sadonufxjh-JVqjx8nO6GmDdoohvtEQabM90GqMaca-t3P4sWty2dk-4fqPK_JSb5-rfdYcdg_VpskCBzlnUjshCsOxdSV0rUHftc5KbYVQuvVcgWkdZ94CaOlBoUbmPNemK1pprBMrcvPbDYh4_JzCYKfT8X9cfAOaVE9P
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/WCNC57260.2024.10571149
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350303582
EISSN 1558-2612
EndPage 6
ExternalDocumentID 10571149
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62272266,62132009
  funderid: 10.13039/501100001809
GroupedDBID 29I
6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i204t-46c33782ebc90fb8edfbca46a3356bd2508bc21da0064d05e6e1cd268f7b48ac3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001268569303143&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 02:04:52 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-46c33782ebc90fb8edfbca46a3356bd2508bc21da0064d05e6e1cd268f7b48ac3
PageCount 6
ParticipantIDs ieee_primary_10571149
PublicationCentury 2000
PublicationDate 2024-April-21
PublicationDateYYYYMMDD 2024-04-21
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-April-21
  day: 21
PublicationDecade 2020
PublicationTitle IEEE Wireless Communications and Networking Conference : [proceedings] : WCNC
PublicationTitleAbbrev WCNC
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020544
Score 2.253499
Snippet Recent advances in space technology have prompted the emergence of numerous Low Earth Orbit (LEO) satellites, producing mega-constellations that can pro-vide...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Adaptation models
Federated learning
Satellites
Schedules
Simulation
Training
Title Hermes: Fast Semi-Asynchronous Federated Learning in LEO Constellations
URI https://ieeexplore.ieee.org/document/10571149
WOSCitedRecordID wos001268569303143&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/eLvHCXMwlV05T8MwFLZoxQALVxG3PLCmTWLHsdlQ1dChKpW4ulU-XlAGUtSkSPx7bDctMDCwWZYsS8-S3_eO73sIXSegqI1vooDFXAaU6jgQ4DNxIlFEcCU9j_t5lI7HfDoVk4as7rkwAOCbz6Drlr6Wb-Z66VJlPTeT1uJ30UKtNGUrstYmurLYgzYNXFEoei_9cT9JLVq3MWBMu-ujv4aoeB-S7f3z9n3U-Wbj4cnGzxygLSgP0e4PIcEjdDe0HyxUNziTVY0f4K0IbqvPUjvlWxva48xJRlhUaXCjp_qKixKPBvfYDex0RJJV4q6DnrLBY38YNCMSgiIOaR1QpgmxTh6UFmGuOJhcaUmZJCRhylh8w5WOIyMd9DBhAgwibWLG81RRLjU5Ru1yXsIJwkLnjBOjCWfCenkuQiG5PaA05BZDmlPUcTaZva9UMGZrc5z9sX-OdpzlXeUlji5Qu14s4RJt64-6qBZX_u2-AA4Xmbw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA46BfXi18Rvc_DarU3SLPEmY3VirQOn7jbyVenBTtZO8N-bdN3UgwdvIRACbyDv8348zwvAZWgksfFN4FHEhEeIQh43VSaOhxJzJkXF436OO0nCRiM-qMnqFRfGGFM1n5mWW1a1fD1RM5cqa7uZtBa_81WwFhKC_DldaxlfWfRB6hauwOftl27SDTsWr9soEJHW4vCvMSqVF4m2_3n_Dmh-8_HgYOlpdsGKyffA1g8pwX1w07dfrCmuYCSKEj6at8y7Lj5z5bRvbXAPIycaYXGlhrWi6ivMchj3HqAb2emoJPPUXRM8Rb1ht-_VQxK8DPmk9AhVGFs3b6TifiqZ0alUglCBcUiltgiHSYUCLRz40H5oqAmURpSlHUmYUPgANPJJbg4B5CqlDGuFGeXWzzPuc8HsAalMalGkPgJNZ5Px-1wHY7wwx_Ef-xdgoz-8j8fxbXJ3AjbdK7g6DApOQaOczswZWFcfZVZMz6t3_AI9s50D
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+Wireless+Communications+and+Networking+Conference+%3A+%5Bproceedings%5D+%3A+WCNC&rft.atitle=Hermes%3A+Fast+Semi-Asynchronous+Federated+Learning+in+LEO+Constellations&rft.au=Chen%2C+Yan&rft.au=Liu%2C+Jun&rft.au=Zhao%2C+Jiejie&rft.au=Jiang%2C+Guanjun&rft.date=2024-04-21&rft.pub=IEEE&rft.eissn=1558-2612&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FWCNC57260.2024.10571149&rft.externalDocID=10571149