LayerCFL: an efficient federated learning with layer-wised clustering
Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential...
Saved in:
Published in | Cybersecurity (Singapore) Vol. 6; no. 1; pp. 39 - 14 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
Singapore
Springer Nature Singapore
01.12.2023
Springer Nature B.V SpringerOpen |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency. |
---|---|
AbstractList | Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency. Abstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency. Abstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency. |
ArticleNumber | 39 |
Author | Yuan, Jie Sun, Mingliang Qian, Rui Li, Jirui Li, Xiaoyong Yuan, Tingting |
Author_xml | – sequence: 1 givenname: Jie surname: Yuan fullname: Yuan, Jie organization: School of Cyberspace Security, Beijing University of Posts and Telecommunications, Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education – sequence: 2 givenname: Rui surname: Qian fullname: Qian, Rui organization: School of Cyberspace Security, Beijing University of Posts and Telecommunications, Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education – sequence: 3 givenname: Tingting orcidid: 0000-0002-9238-064X surname: Yuan fullname: Yuan, Tingting email: tingting.yuan@cs.uni-goettingen.de organization: Institute of Computer Science, Faculty of Mathematics and Computer Science, University of Goettingen – sequence: 4 givenname: Mingliang surname: Sun fullname: Sun, Mingliang organization: School of Cyberspace Security, Beijing University of Posts and Telecommunications, Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education – sequence: 5 givenname: Jirui surname: Li fullname: Li, Jirui organization: School of Information Technology, Henan University of Chinese Medicine – sequence: 6 givenname: Xiaoyong surname: Li fullname: Li, Xiaoyong organization: School of Cyberspace Security, Beijing University of Posts and Telecommunications, Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education |
BookMark | eNp9kDFPwzAQhS1UJErpH2CKxBywz04cs6GqhUqRWGC2XOdcUoWk2Klo_z1ug4AJeTj77r131ndJRm3XIiHXjN4yVuR3QYCgNKXAU0qZhHR_RsaQxScHkY_-3C_INIQNpRSk4kKKMZmX5oB-tijvE9Mm6Fxta2z7xGGF3vRYJQ0a39btOvms-7ekOcrTzzrEiW12oUcfZ1fk3Jkm4PS7TsjrYv4ye0rL58fl7KFMbUahTx3jwCg4gdRivnLoWFVxNApEBS4vTIZKoMwLRwuLnK8EGJRiFY8wsFJ8QpZDbtWZjd76-t34g-5MrU-Nzq-18X1tG9RCqsLZTMochIiJCrLMFTJujzRMBTHrZsja-u5jh6HXm27n2_h9DYXKMxUJ0aiCQWV9F4JH97OVUX2krwf6OtLXJ_p6H018MIXtkQ763-h_XF9TM4hb |
CitedBy_id | crossref_primary_10_1145_3674973 |
Cites_doi | 10.1016/j.bdr.2015.04.001 10.1007/s11036-022-01978-8 10.1016/j.future.2020.10.007 10.1145/3298981 10.1109/MSP.2020.2975749 10.1145/3436755 10.1145/3558005 10.1016/j.inffus.2022.07.024 10.1016/j.future.2022.05.003 10.1561/2200000083 10.1016/j.neucom.2017.01.026 10.1109/IJCNN.2017.7966217 10.1007/978-3-319-10590-1_53 10.1109/CVPR52688.2022.00985 10.1109/INFOCOM41043.2020.9155494 10.1109/ISBI.2019.8759317 10.1038/s41467-022-30714-9 10.1007/978-3-319-57959-7_1 10.1145/3488560.3501396 10.1016/j.neucom.2021.07.098 10.1109/ICUFN49451.2021.9528575 10.1109/ICDE53745.2022.00077 10.1007/978-3-030-23551-2_2 10.1145/3458864.3467681 |
ContentType | Journal Article |
Copyright | The Author(s) 2023 The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: The Author(s) 2023 – notice: The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | C6C AAYXX CITATION 7SC 8FD ABUWG AFKRA AZQEC BENPR CCPQU DWQXO JQ2 L7M L~C L~D PIMPY PQEST PQQKQ PQUKI PRINS DOA |
DOI | 10.1186/s42400-023-00172-x |
DatabaseName | SpringerOpen CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Publicly Available Content Database Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central China Computer and Information Systems Abstracts Professional ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest One Academic Advanced Technologies Database with Aerospace |
DatabaseTitleList | CrossRef Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: C6C name: SpringerOpen url: http://www.springeropen.com/ sourceTypes: Publisher – sequence: 2 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 3 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 2523-3246 |
EndPage | 14 |
ExternalDocumentID | oai_doaj_org_article_4798fc577624468f9255f8702f252ad2 10_1186_s42400_023_00172_x |
GrantInformation_xml | – fundername: the National Natural Science Foundation of China grantid: 62002028 |
GroupedDBID | AAFWJ AAKKN AAYZJ ACACY ADBBV AFGXO AFKRA AFNRJ AFPKN AHBXF ALMA_UNASSIGNED_HOLDINGS AMKLP ARCSS BCNDV BENPR C24 C6C CCPQU EBS GROUPED_DOAJ IAO ISR M~E OK1 PIMPY PROAC RSV SOJ 0R~ AAYXX ABEEZ ACULB CITATION ITC 7SC 8FD ABUWG AZQEC DWQXO JQ2 L7M L~C L~D PQEST PQQKQ PQUKI PRINS |
ID | FETCH-LOGICAL-c502t-f132102f4e0ce6bfef1dd3ea924d2f68a5e94e768f08ce33b42ae74b4b44a2b93 |
IEDL.DBID | BENPR |
ISSN | 2523-3246 |
IngestDate | Tue Oct 22 15:15:00 EDT 2024 Thu Oct 10 17:43:34 EDT 2024 Thu Sep 26 19:14:10 EDT 2024 Sat Dec 16 12:03:29 EST 2023 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Keywords | Clustered federated learning Federated learning Layer-wised clustering Non-IID |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c502t-f132102f4e0ce6bfef1dd3ea924d2f68a5e94e768f08ce33b42ae74b4b44a2b93 |
ORCID | 0000-0002-9238-064X |
OpenAccessLink | https://www.proquest.com/docview/2896599340?pq-origsite=%requestingapplication% |
PQID | 2896599340 |
PQPubID | 4403480 |
PageCount | 14 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_4798fc577624468f9255f8702f252ad2 proquest_journals_2896599340 crossref_primary_10_1186_s42400_023_00172_x springer_journals_10_1186_s42400_023_00172_x |
PublicationCentury | 2000 |
PublicationDate | 2023-12-01 |
PublicationDateYYYYMMDD | 2023-12-01 |
PublicationDate_xml | – month: 12 year: 2023 text: 2023-12-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Singapore |
PublicationPlace_xml | – name: Singapore |
PublicationTitle | Cybersecurity (Singapore) |
PublicationTitleAbbrev | Cybersecurity |
PublicationYear | 2023 |
Publisher | Springer Nature Singapore Springer Nature B.V SpringerOpen |
Publisher_xml | – name: Springer Nature Singapore – name: Springer Nature B.V – name: SpringerOpen |
References | Gong, Xing, Liu, Wang, Liu (CR8) 2022; 27 Li, Sahu, Zaheer, Sanjabi, Talwalkar, Smith (CR15) 2020; 2 Sattler, Muller, Samek (CR29) 2020; PP CR19 Yang, Huang, Lin, Cao (CR36) 2022 CR16 CR38 CR13 CR35 CR12 CR11 CR33 CR10 CR32 Liu, Ding, Shaham, Rahayu, Farokhi, Lin (CR17) 2021; 54 CR31 CR30 Yang, Liu, Chen, Tong (CR37) 2019; 10 Mothukuri, Parizi, Pouriyeh, Huang, Dehghantanha, Srivastava (CR25) 2021; 115 Zhou, Pan, Wang, Vasilakos (CR42) 2017; 237 Criado, Casado, Iglesias, Regueiro, Barro (CR4) 2022; 88 CR2 Kairouz, McMahan, Avent, Bellet, Bennis, Bhagoji, Bonawitz, Charles, Cormode, Cummings (CR9) 2021; 14 Li, Sahu, Talwalkar, Smith (CR14) 2020; 37 CR3 CR6 CR5 Ghosh, Chung, Yin, Ramchandran (CR7) 2020; 33 Al-Jarrah, Yoo, Muhaidat, Karagiannidis, Taha (CR1) 2015; 2 CR28 CR27 CR26 Ma, Zhu, Lin, Chen, Qin (CR21) 2022 CR24 CR23 CR22 CR43 CR20 CR41 CR40 Wang, Han, Wang, Zhao, Chen (CR34) 2019; PP Yosinski, Clune, Bengio, Lipson (CR39) 2014 Liu, Wu, Ge, Fan, Zou (CR18) 2020; 34 172_CR41 T Li (172_CR15) 2020; 2 172_CR40 T Li (172_CR14) 2020; 37 X Ma (172_CR21) 2022 L Yang (172_CR36) 2022 B Liu (172_CR17) 2021; 54 L Zhou (172_CR42) 2017; 237 A Ghosh (172_CR7) 2020; 33 MF Criado (172_CR4) 2022; 88 172_CR19 172_CR13 172_CR35 J Yosinski (172_CR39) 2014 172_CR16 172_CR38 172_CR10 172_CR32 172_CR31 172_CR12 172_CR11 172_CR33 V Mothukuri (172_CR25) 2021; 115 F Sattler (172_CR29) 2020; PP 172_CR30 172_CR2 172_CR3 172_CR5 172_CR6 F Liu (172_CR18) 2020; 34 Q Yang (172_CR37) 2019; 10 172_CR28 OY Al-Jarrah (172_CR1) 2015; 2 X Wang (172_CR34) 2019; PP 172_CR24 172_CR27 172_CR26 B Gong (172_CR8) 2022; 27 172_CR43 172_CR20 172_CR23 P Kairouz (172_CR9) 2021; 14 172_CR22 |
References_xml | – ident: CR22 – ident: CR43 – year: 2014 ident: CR39 publication-title: How transferable are features in deep neural networks? contributor: fullname: Lipson – volume: 2 start-page: 87 issue: 3 year: 2015 end-page: 93 ident: CR1 article-title: Efficient machine learning for big data: a review publication-title: Big Data Res doi: 10.1016/j.bdr.2015.04.001 contributor: fullname: Taha – ident: CR2 – ident: CR16 – volume: 27 start-page: 1520 issue: 4 year: 2022 end-page: 1530 ident: CR8 article-title: Adaptive clustered federated learning for heterogeneous data in edge computing publication-title: Mobile Networks Appl doi: 10.1007/s11036-022-01978-8 contributor: fullname: Liu – ident: CR12 – volume: PP start-page: 1 issue: 99 year: 2020 end-page: 13 ident: CR29 article-title: Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints publication-title: IEEE Transactions on Neural Networks and Learning Systems contributor: fullname: Samek – ident: CR30 – ident: CR10 – ident: CR33 – ident: CR35 – ident: CR6 – volume: 115 start-page: 619 year: 2021 end-page: 640 ident: CR25 article-title: A survey on security and privacy of federated learning publication-title: Futur Gener Comput Syst doi: 10.1016/j.future.2020.10.007 contributor: fullname: Srivastava – volume: 10 start-page: 1 issue: 2 year: 2019 end-page: 19 ident: CR37 article-title: Federated machine learning: Concept and applications publication-title: ACM Transactions on Intelligent Systems and Technology doi: 10.1145/3298981 contributor: fullname: Tong – volume: 37 start-page: 50 issue: 3 year: 2020 end-page: 60 ident: CR14 article-title: Federated learning: challenges, methods, and future directions publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2020.2975749 contributor: fullname: Smith – volume: 54 start-page: 1 issue: 2 year: 2021 end-page: 36 ident: CR17 article-title: When machine learning meets privacy: a survey and outlook publication-title: ACM Comput Surv (CSUR) doi: 10.1145/3436755 contributor: fullname: Lin – ident: CR40 – ident: CR27 – ident: CR23 – year: 2022 ident: CR36 article-title: Personalized federated learning on non-iid data via group-based meta-learning publication-title: ACM Trans Knowl Discov Data just Accepted doi: 10.1145/3558005 contributor: fullname: Cao – ident: CR19 – volume: PP start-page: 1 issue: 99 year: 2019 end-page: 10 ident: CR34 article-title: In-edge ai: Intelligentizing mobile edge computing, caching and communication by federated learning publication-title: IEEE Network contributor: fullname: Chen – volume: 34 start-page: 11572 year: 2020 end-page: 11579 ident: CR18 article-title: Federated learning for vision-and-language grounding problems publication-title: Proc AAAI Conf Artif Intell contributor: fullname: Zou – volume: 88 start-page: 263 year: 2022 end-page: 280 ident: CR4 article-title: Non-iid data and continual learning processes in federated learning: a long road ahead publication-title: Inform Fusion doi: 10.1016/j.inffus.2022.07.024 contributor: fullname: Barro – year: 2022 ident: CR21 publication-title: A state-of-the-art survey on solving non-iid data in federated learning doi: 10.1016/j.future.2022.05.003 contributor: fullname: Qin – ident: CR3 – ident: CR38 – volume: 14 start-page: 1 issue: 1–2 year: 2021 end-page: 210 ident: CR9 article-title: Advances and open problems in federated learning publication-title: Foundations and Trends® in Machine Learning doi: 10.1561/2200000083 contributor: fullname: Cummings – volume: 2 start-page: 429 year: 2020 end-page: 450 ident: CR15 article-title: Federated optimization in heterogeneous networks publication-title: Proc Mach Learn Syst contributor: fullname: Smith – volume: 237 start-page: 350 year: 2017 end-page: 361 ident: CR42 article-title: Machine learning on big data: Opportunities and challenges publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.01.026 contributor: fullname: Vasilakos – ident: CR31 – ident: CR13 – ident: CR11 – ident: CR32 – ident: CR5 – ident: CR28 – ident: CR41 – ident: CR26 – ident: CR24 – volume: 33 start-page: 19,586 year: 2020 end-page: 19,597 ident: CR7 article-title: An efficient framework for clustered federated learning publication-title: Adv Neural Inf Process Syst contributor: fullname: Ramchandran – ident: CR20 – ident: 172_CR3 doi: 10.1109/IJCNN.2017.7966217 – ident: 172_CR40 doi: 10.1007/978-3-319-10590-1_53 – ident: 172_CR19 – volume: 88 start-page: 263 year: 2022 ident: 172_CR4 publication-title: Inform Fusion doi: 10.1016/j.inffus.2022.07.024 contributor: fullname: MF Criado – ident: 172_CR23 – ident: 172_CR2 – ident: 172_CR20 doi: 10.1109/CVPR52688.2022.00985 – volume: 54 start-page: 1 issue: 2 year: 2021 ident: 172_CR17 publication-title: ACM Comput Surv (CSUR) doi: 10.1145/3436755 contributor: fullname: B Liu – volume: 14 start-page: 1 issue: 1–2 year: 2021 ident: 172_CR9 publication-title: Foundations and Trends® in Machine Learning doi: 10.1561/2200000083 contributor: fullname: P Kairouz – ident: 172_CR10 – ident: 172_CR33 doi: 10.1109/INFOCOM41043.2020.9155494 – volume: 33 start-page: 19,586 year: 2020 ident: 172_CR7 publication-title: Adv Neural Inf Process Syst contributor: fullname: A Ghosh – ident: 172_CR31 – ident: 172_CR30 doi: 10.1109/ISBI.2019.8759317 – ident: 172_CR12 – ident: 172_CR16 – volume-title: A state-of-the-art survey on solving non-iid data in federated learning year: 2022 ident: 172_CR21 doi: 10.1016/j.future.2022.05.003 contributor: fullname: X Ma – volume: 237 start-page: 350 year: 2017 ident: 172_CR42 publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.01.026 contributor: fullname: L Zhou – ident: 172_CR5 – volume: 27 start-page: 1520 issue: 4 year: 2022 ident: 172_CR8 publication-title: Mobile Networks Appl doi: 10.1007/s11036-022-01978-8 contributor: fullname: B Gong – volume: PP start-page: 1 issue: 99 year: 2020 ident: 172_CR29 publication-title: IEEE Transactions on Neural Networks and Learning Systems contributor: fullname: F Sattler – ident: 172_CR35 doi: 10.1038/s41467-022-30714-9 – ident: 172_CR32 doi: 10.1007/978-3-319-57959-7_1 – ident: 172_CR24 – volume: 2 start-page: 429 year: 2020 ident: 172_CR15 publication-title: Proc Mach Learn Syst contributor: fullname: T Li – ident: 172_CR22 – ident: 172_CR41 – ident: 172_CR6 doi: 10.1145/3488560.3501396 – ident: 172_CR26 – ident: 172_CR43 doi: 10.1016/j.neucom.2021.07.098 – ident: 172_CR28 – volume-title: How transferable are features in deep neural networks? year: 2014 ident: 172_CR39 contributor: fullname: J Yosinski – ident: 172_CR11 doi: 10.1109/ICUFN49451.2021.9528575 – volume: 10 start-page: 1 issue: 2 year: 2019 ident: 172_CR37 publication-title: ACM Transactions on Intelligent Systems and Technology doi: 10.1145/3298981 contributor: fullname: Q Yang – ident: 172_CR13 doi: 10.1109/ICDE53745.2022.00077 – volume: PP start-page: 1 issue: 99 year: 2019 ident: 172_CR34 publication-title: IEEE Network contributor: fullname: X Wang – ident: 172_CR38 doi: 10.1007/978-3-030-23551-2_2 – volume: 37 start-page: 50 issue: 3 year: 2020 ident: 172_CR14 publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2020.2975749 contributor: fullname: T Li – year: 2022 ident: 172_CR36 publication-title: ACM Trans Knowl Discov Data just Accepted doi: 10.1145/3558005 contributor: fullname: L Yang – volume: 115 start-page: 619 year: 2021 ident: 172_CR25 publication-title: Futur Gener Comput Syst doi: 10.1016/j.future.2020.10.007 contributor: fullname: V Mothukuri – volume: 34 start-page: 11572 year: 2020 ident: 172_CR18 publication-title: Proc AAAI Conf Artif Intell contributor: fullname: F Liu – volume: 2 start-page: 87 issue: 3 year: 2015 ident: 172_CR1 publication-title: Big Data Res doi: 10.1016/j.bdr.2015.04.001 contributor: fullname: OY Al-Jarrah – ident: 172_CR27 doi: 10.1145/3458864.3467681 |
SSID | ssj0002793474 |
Score | 2.293755 |
Snippet | Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this... Abstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address... Abstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address... |
SourceID | doaj proquest crossref springer |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 39 |
SubjectTerms | Accuracy Clients Clustered federated learning Clustering Computer Applications Computer Science Cybercrime Cybersecurity Federated learning Internet Layer-wised clustering Medical research Neural networks Non-IID Research methodology |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PS8MwFA6ykxdRVKxOycGbhrVp0qbedGwMmZ4c7BbyU5QxxW24P9-XtFUniBfprUkhfC_p-77k5T2EzhW1YGmqiLUeBEqWG6JEpkhgc7kGgsp82Bq4uy9GE3Y75dNvpb5CTFidHrgGrsfKSnjDS1i0oFyEr4ADe5hk1FNOla3_vhn_Jqae43FalbOStbdkRNFbsBAtScBFkah7yHrDE8WE_Rss88fBaPQ3w1200xBFfF0PcA9tufk-GowVUOT-cHyF1Ry7mP4BvAb2ISUEsEaLmyoQjzhssOJZ6E7enxbQYmarkBQB2g7QZDh46I9IUwiBGJ7SJfFZuGlDPXOpcYX2zmfW5k6BdrLUF0JxVzEHwsGnwrg814wqVzIND1NUV_kh6sxf5u4I4SzwE8e0FvCJCcX8DOei8Mr4kru8TNBFC4p8rfNdyKgTRCFrCCVAKCOEcp2gm4DbZ8-Qqzq-AAvKxoLyLwsmqNuiLpsFtJCgAwsO3ImlCbpsLfHV_PuQjv9jSCdoO5SVr8NWuqizfFu5UyAfS30W59kHiXjR7A priority: 102 providerName: Directory of Open Access Journals – databaseName: Springer Nature OA Free Journals dbid: C24 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5SL158i6tVcvCmwd08drPetLQUqZ4s9Bay2aQopZU-0J_vJLtrqehB9pYHLDOZzPclmRmErjQtQdNUk7J0QFASZoiWiSYezbECACp3_mjg6TntD_njSIzWcdzhsXtzIxk26mDVMr1dcP_akYCLIYG3EACO2x48-GXdqUMc3sJNWs54xpsAmV-nbjihkKt_A2D-uBMNrqa3j3ZrjIjvK6UeoC07PUR7Tf0FXJvjEeoONADmTm9wh_UU25AMAnwIdj5BBGDIEtc1IcbYH7fiiR9OPl4X0GMmK58iAfqO0bDXfen0SV0WgRgR0yVxiY-7oY7b2Ni0cNYlZcmsBiZVUpdKLWzOLdAIF0tjGSs41TbjBXxc0yJnJ6g1nU3tKcKJRyuWF4WEKcaX9jNCyNRp4zJhWRah60ZO6r3KfqECa5CpqqSqQKoqSFV9RujBi_J7pM9cHRpm87GqDUHxLJfOiAw2YWCi0uXAaRxsGtRRQXVJI9RuFKFqc1ooYIWpACTF4wjdNMpZd__9S2f_G36Odnw5-eq5Shu1lvOVvQDQsSwuwyL7AleWzgA priority: 102 providerName: Springer Nature |
Title | LayerCFL: an efficient federated learning with layer-wised clustering |
URI | https://link.springer.com/article/10.1186/s42400-023-00172-x https://www.proquest.com/docview/2896599340 https://doaj.org/article/4798fc577624468f9255f8702f252ad2 |
Volume | 6 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSyQxEC58XLy4rg8cdYccvGlwOp10Z7yIDjPIoiKi4C2k8xBBZtQZWX--VZm04sIuDX3opJumKqn6vkpSBbBvhUdNC8u9j0hQitJxqwvLCc2VDQJUGSk0cHlVnd_J3_fqPgfcpnlbZWsTk6H2E0cx8iMkBpVCZyp7J88vnKpG0epqLqGxCMuikLRMu3w2vLq--YyyCBx-spbtaRldHU0l7Zrk6Kp44j_8_ZtHSon7v6HNvxZIk98ZrcFqBozsdK7hn7AQxuvwoy3GwPLc3IDhhUX0PBhdHDM7ZiFlhkCHwiJli0BA6VkuEPHAKPbKnqg7__M4xRb39Eb5ErBtE-5Gw9vBOc81ErhTPTHjsaBDOCLK0HOhamKIhfdlsEirvIiVtir0ZUBOEXvahbJspLChlg1e0oqmX27B0ngyDtvACoIuQTaNxlcc1flzSukqWhdrFcq6AwetnMzzPBWGSRRCV2YuVYNSNUmq5r0DZyTKz56Uxjo9mLw-mDwrjKz7OjpVo0VGWqpjHwlORAsiolDCetGBvVYRJs-tqfkaCR04bJXz1fzvX9r5_9d2YYVqyc_3quzB0uz1LfxCxDFrunlYdWFxICTdq0E3sfcPtbPVYA |
link.rule.ids | 315,786,790,870,2115,21416,27955,27956,33777,41152,41153,42221,42222,43838,51609,52266 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LTxsxEB7RcKCXUl5qCm194AYWWa-963CpCkoUIEQIgcTN8vqBKqGEkkTNz2dm4wVRiWpva3u1mrFnvm9szwDsW-FR08Jy7yMSlCx33OrMckJzeYUAVUYKDVyOisGtPL9TdyngNk3HKhubWBtqP3EUIz9CYlAodKay8_PxD6eqUbS7mkpofIBVSrmpW7B60htdXb9EWQROP1nK5raMLo6mkk5NcnRVvOY_fPHGI9WJ-9-gzX82SGu_0_8MnxJgZL-WGt6AlTDehPWmGANLa3MLekOL6Pm0PzxmdsxCnRkCHQqLlC0CAaVnqUDEPaPYK3ug7vzv7ym2uIc55UvAtm247fduTgc81UjgTnXEjMeMLuGIKEPHhaKKIWbe58EirfIiFtqq0JUBOUXsaBfyvJLChlJW-Egrqm6-A63xZBy-AMsIugRZVRqHOKrz55TSRbQulirkZRsOGjmZx2UqDFNTCF2YpVQNStXUUjWLNpyQKF96Uhrr-sXk6d6kVWFk2dXRqRItMtJSHbtIcCJaEBGFEtaLNuw1ijBpbU3N60xow2GjnNfm93_p6_-_9gPWBjeXQzM8G13swkeqK788t7IHrdnTPHxD9DGrvqcp9gzsFNW6 |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEA6iIF58i_WZgzcNbtOkTb3puouPdfHggreQ5iGKdBd3RX--k7RVV_QgvTUJtDOd5vuSzDcIHShqwNNUEWMcEJQ40USJWBGP5pICACpzfmngpp9eDNjVPb__lsUfTrs3W5JVToNXaSonxyPjqhAX6fGY-aOPBOYbEkgMARQ5xwDc-BoG7Trf4Slsq-UJy1iTLfPr0KkZKQj3T6HNHxukYd7pLqPFGjDi08rDK2jGlqtoqSnGgOvYXEOdngL03O72TrAqsQ3KEPBC2Hm1CACUBtcFIh6wX3vFz747eXscQ4t-fvV6CdC2jgbdzl37gtQ1EojmLTohLvZJONQx29I2LZx1sTGJVUCrDHWpUNzmzAKncC2hbZIUjCqbsQIupmiRJxtothyWdhPh2EMXy4pCwBDt6_xpzkXqlHYZt0kWocPGTnJUSWHIQCFEKiurSrCqDFaV7xE686b87OllrMON4cuDrKNCsiwXTvMM_shAS4XLgeA4-INQRzlVhkZop3GErGNrLIEiphxgFWtF6Khxzlfz34-09b_u-2j-9rwre5f962204MvMV8dYdtDs5OXV7gIYmRR74Xv7AKW71Zk |
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=LayerCFL%3A+an+efficient+federated+learning+with+layer-wised+clustering&rft.jtitle=Cybersecurity+%28Singapore%29&rft.au=Yuan%2C+Jie&rft.au=Qian%2C+Rui&rft.au=Yuan%2C+Tingting&rft.au=Sun%2C+Mingliang&rft.date=2023-12-01&rft.pub=Springer+Nature+B.V&rft.eissn=2523-3246&rft.volume=6&rft.issue=1&rft.spage=39&rft_id=info:doi/10.1186%2Fs42400-023-00172-x |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2523-3246&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2523-3246&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2523-3246&client=summon |