Benchmark for Personalized Federated Learning
Federated learning is a distributed machine learning approach that allows a single server to collaboratively build machine learning models with multiple clients without sharing datasets. Since data distributions may differ across clients, data heterogeneity is a challenging issue in federated learni...
Saved in:
Published in | IEEE open journal of the Computer Society Vol. 5; pp. 1 - 12 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
New York
IEEE
01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Federated learning is a distributed machine learning approach that allows a single server to collaboratively build machine learning models with multiple clients without sharing datasets. Since data distributions may differ across clients, data heterogeneity is a challenging issue in federated learning. To address this issue, numerous federated learning methods have been proposed to build personalized models for clients, referred to as personalized federated learning. Nevertheless, no studies comprehensively investigate the performance of personalized federated learning methods in various experimental settings such as datasets and client settings. Therefore, in this article, we aim to benchmark the performance of existing personalized federated learning methods in various settings. We first survey the experimental settings in existing studies. We then benchmark the performance of existing methods through comprehensive experiments to reveal their characteristics in computer vision and natural language processing tasks which are the most popular tasks based on our survey. Our experimental study shows that (i) large data heterogeneity often leads to highly accurate predictions and (ii) standard federated learning methods (e.g. FedAvg) with fine-tuning often outperform personalized federated learning methods. |
---|---|
AbstractList | Federated learning is a distributed machine learning approach that allows a single server to collaboratively build machine learning models with multiple clients without sharing datasets. Since data distributions may differ across clients, data heterogeneity is a challenging issue in federated learning. To address this issue, numerous federated learning methods have been proposed to build personalized models for clients, referred to as personalized federated learning. Nevertheless, no studies comprehensively investigate the performance of personalized federated learning methods in various experimental settings such as datasets and client settings. Therefore, in this article, we aim to benchmark the performance of existing personalized federated learning methods in various settings. We first survey the experimental settings in existing studies. We then benchmark the performance of existing methods through comprehensive experiments to reveal their characteristics in computer vision and natural language processing tasks which are the most popular tasks based on our survey. Our experimental study shows that (i) large data heterogeneity often leads to highly accurate predictions and (ii) standard federated learning methods (e.g. FedAvg) with fine-tuning often outperform personalized federated learning methods. |
Author | Sasaki, Yuya Xiao, Chuan Matsuda, Koji Onizuka, Makoto |
Author_xml | – sequence: 1 givenname: Koji surname: Matsuda fullname: Matsuda, Koji organization: Osaka University, Suita, Osaka, Japan – sequence: 2 givenname: Yuya orcidid: 0000-0002-8548-3181 surname: Sasaki fullname: Sasaki, Yuya organization: Osaka University, Suita, Osaka, Japan – sequence: 3 givenname: Chuan surname: Xiao fullname: Xiao, Chuan organization: Osaka University, Suita, Osaka, Japan – sequence: 4 givenname: Makoto orcidid: 0000-0001-5559-8300 surname: Onizuka fullname: Onizuka, Makoto organization: Osaka University, Suita, Osaka, Japan |
BookMark | eNpNUMtOwzAQtBBIvPoBSBwqcU7xem0nOUJFoagSSMDZsuM1pJQYnHCArychFeK0D83M7swh221iQ4ydAJ8B8PL87nb-MBNc4AwRBSrYYQdCS5mB0MXuv36fTdp2zTkXCgBQHbDskprq5c2m12mIaXpPqY2N3dTf5KcL8pRs13crsqmpm-djthfspqXJth6xp8XV4_wmW91dL-cXq6ySHLssgELhhQraueDBVUoDFkoJYSkvbUVWlFqFwnns50qSzp2T4LySouTO4RFbjro-2rV5T3X_4JeJtja_i5iejU1dXW3ICEmoc5IqoJWVKgqfewtQUAnBB5S91tmo9Z7ixye1nVnHz9R7bE1_LFcSUaseBSOqSrFtE4W_q8DNELIZQjZDyGYbcs85HTk1Ef3DI-jB8A_KxXgZ |
CODEN | IOJCB2 |
CitedBy_id | crossref_primary_10_1007_s13042_024_02234_z |
Cites_doi | 10.1609/aaai.v35i9.16960 10.1109/OJCS.2020.2993259 10.1109/TNNLS.2020.3015958 10.1145/3369583.3392686 10.1145/3517207.3526969 10.1109/CVPR52729.2023.00383 10.1145/3534678.3539112 10.3115/v1/D14-1162 10.1109/ICCV.2017.76 10.1109/IJCNN48605.2020.9207469 10.3390/app10082864 10.1109/ICDE53745.2022.00077 10.1016/j.jpdc.2004.03.020 10.1109/CVPR52688.2022.00992 10.1609/aaai.v34i04.5895 10.1137/1.9781611977172.52 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D DOA |
DOI | 10.1109/OJCS.2023.3332351 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Computer and Information Systems Abstracts |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 2644-1268 |
EndPage | 12 |
ExternalDocumentID | oai_doaj_org_article_24e367e45f3a4c588d7da118e91fdf34 10_1109_OJCS_2023_3332351 10316561 |
Genre | orig-research |
GroupedDBID | 0R~ 97E AAJGR ABVLG ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ IEDLZ JAVBF M~E OCL OK1 RIA RIC RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c403t-f1532d25f6bbfd1bc561385522ae79acea2965f8bd3e79c4e67bb41bd54290bb3 |
IEDL.DBID | DOA |
ISSN | 2644-1268 |
IngestDate | Tue Oct 22 15:15:35 EDT 2024 Thu Oct 10 20:04:46 EDT 2024 Fri Aug 23 03:23:04 EDT 2024 Wed Jun 26 19:24:16 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c403t-f1532d25f6bbfd1bc561385522ae79acea2965f8bd3e79c4e67bb41bd54290bb3 |
ORCID | 0000-0001-5559-8300 0000-0002-8548-3181 0009-0009-9645-4894 0000-0001-7239-5134 |
OpenAccessLink | https://doaj.org/article/24e367e45f3a4c588d7da118e91fdf34 |
PQID | 2907543365 |
PQPubID | 5075782 |
PageCount | 12 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_24e367e45f3a4c588d7da118e91fdf34 proquest_journals_2907543365 crossref_primary_10_1109_OJCS_2023_3332351 ieee_primary_10316561 |
PublicationCentury | 2000 |
PublicationDate | 2024-01-01 |
PublicationDateYYYYMMDD | 2024-01-01 |
PublicationDate_xml | – month: 01 year: 2024 text: 2024-01-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | New York |
PublicationPlace_xml | – name: New York |
PublicationTitle | IEEE open journal of the Computer Society |
PublicationTitleAbbrev | OJCS |
PublicationYear | 2024 |
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 | Reddi (ref42) 2021 ref53 Ozkara (ref40) 2021 Lin (ref35) 2020 ref54 Achituve (ref3) 2021 Arivazhagan (ref4) 2019 ref17 ref16 ref18 Corinzia (ref13) 2019 Li (ref31) 2021 Mansour (ref36) 2020 Collins (ref12) 2021 Smith (ref48) 2017 Wang (ref52) 2020 Diao (ref15) 2021 Dinh (ref50) 2020 Jiang (ref25) 2019 Acar (ref2) 2021 ref41 ref44 ref43 Li (ref28) 2019 Liang (ref34) 2020 Yurochkin (ref55) 2019 ref7 ref9 Chen (ref10) 2022 Li (ref33) 2019 ref5 Fallah (ref19) 2020 Li (ref32) 2020 Zhu (ref58) 2021 Shoham (ref46) 2019 ref30 Zhang (ref57) 2021 McMahan (ref39) 2017 ref1 Caldas (ref8) 2018 Singhal (ref47) 2021 Wang (ref51) 2020 ref38 Sun (ref49) 2021 Dai (ref14) 2020 Marfoq (ref37) 2021 Hanzely (ref20) 2020 Chen (ref11) 2021 ref24 Shen (ref45) 2020 Huang (ref23) 2021 He (ref21) 2020 Karimireddy (ref26) 2020 ref29 Khodak (ref27) 2019 Zhang (ref56) 2021 Beutel (ref6) 2020 Hinton (ref22) 2015 |
References_xml | – start-page: 23309 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref49 article-title: PartialFed: Cross-domain personalized federated learning via partial initialization contributor: fullname: Sun – start-page: 8392 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref3 article-title: Personalized federated learning with Gaussian processes contributor: fullname: Achituve – ident: ref24 doi: 10.1609/aaai.v35i9.16960 – start-page: 5132 volume-title: Proc. 37th Int. Conf. Mach. Learn. year: 2020 ident: ref26 article-title: SCAFFOLD: Stochastic controlled averaging for federated learning contributor: fullname: Karimireddy – ident: ref54 doi: 10.1109/OJCS.2020.2993259 – volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref57 article-title: Personalized federated learning with first order model optimization contributor: fullname: Zhang – ident: ref44 doi: 10.1109/TNNLS.2020.3015958 – volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref15 article-title: HeteroFL Computation and communication efficient federated learning for heterogeneous clients contributor: fullname: Diao – start-page: 6357 volume-title: Proc. Int. Conf. Mach. Learn. year: 2021 ident: ref31 article-title: Ditto: Fair and robust federated learning through personalization contributor: fullname: Li – start-page: 2351 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref35 article-title: Ensemble distillation for robust model fusion in federated learning contributor: fullname: Lin – year: 2020 ident: ref36 article-title: Three approaches for personalization with applications to federated learning contributor: fullname: Mansour – start-page: 7252 volume-title: Proc. Int. Conf. Mach. Learn. year: 2019 ident: ref55 article-title: Bayesian nonparametric federated learning of neural networks contributor: fullname: Yurochkin – ident: ref9 doi: 10.1145/3369583.3392686 – year: 2015 ident: ref22 article-title: Distilling the knowledge in a neural network contributor: fullname: Hinton – start-page: 21 volume-title: Proc. 38th Int. Conf. Mach. Learn. year: 2021 ident: ref2 article-title: Debiasing model updates for improving personalized federated training contributor: fullname: Acar – start-page: 10092 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref56 article-title: Parameterized knowledge transfer for personalized federated learning contributor: fullname: Zhang – start-page: 2304 volume-title: Proc. 34th Int. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref20 article-title: Lower bounds and optimal algorithms for personalized federated learning contributor: fullname: Hanzely – ident: ref1 doi: 10.1145/3517207.3526969 – ident: ref17 doi: 10.1109/CVPR52729.2023.00383 – start-page: 3557 volume-title: Proc. 34th Int. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref19 article-title: Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach contributor: fullname: Fallah – volume-title: Proc. Int. Conf. Learn. Representations year: 2019 ident: ref33 article-title: On the convergence of fedavg on non-IID data contributor: fullname: Li – ident: ref53 doi: 10.1145/3534678.3539112 – start-page: 21394 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref50 article-title: Personalized federated learning with moreau envelopes contributor: fullname: Dinh – volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref11 article-title: FedBE: Making bayesian model ensemble applicable to federated learning contributor: fullname: Chen – ident: ref41 doi: 10.3115/v1/D14-1162 – ident: ref43 doi: 10.1109/ICCV.2017.76 – year: 2020 ident: ref34 article-title: Think locally, act globally: Federated learning with local and global representations contributor: fullname: Liang – start-page: 12878 volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref58 article-title: Data-free knowledge distillation for heterogeneous federated learning contributor: fullname: Zhu – start-page: 5917 volume-title: Proc. 33rd Int. Conf. Neural Inf. Process. Syst. year: 2019 ident: ref27 article-title: Adaptive gradient-based meta-learning methods contributor: fullname: Khodak – start-page: 9687 volume-title: Proc. 34th Int. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref14 article-title: Federated Bayesian optimization via thompson sampling contributor: fullname: Dai – start-page: 11220 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref47 article-title: Federated reconstruction: Partially local federated learning contributor: fullname: Singhal – year: 2019 ident: ref25 article-title: Improving federated learning personalization via model agnostic meta learning contributor: fullname: Jiang – year: 2018 ident: ref8 article-title: LEAF: A benchmark for federated settings contributor: fullname: Caldas – ident: ref7 doi: 10.1109/IJCNN48605.2020.9207469 – volume-title: Proc. Int. Conf. Learn. Representations year: 2020 ident: ref51 article-title: Federated learning with matched averaging contributor: fullname: Wang – start-page: 7611 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref52 article-title: Tackling the objective inconsistency problem in heterogeneous federated optimization contributor: fullname: Wang – ident: ref5 doi: 10.3390/app10082864 – year: 2019 ident: ref46 article-title: Overcoming forgetting in federated learning on non-IID data contributor: fullname: Shoham – year: 2020 ident: ref6 article-title: Flower: A friendly federated learning research framework contributor: fullname: Beutel – start-page: 15434 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref37 article-title: Federated multi-task learning under a mixture of distributions contributor: fullname: Marfoq – year: 2019 ident: ref4 article-title: Federated learning with personalization layers contributor: fullname: Arivazhagan – start-page: 429 volume-title: Proc. Mach. Learn. Syst. year: 2020 ident: ref32 article-title: Federated optimization in heterogeneous networks contributor: fullname: Li – start-page: 4424 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2017 ident: ref48 article-title: Federated multi-task learning contributor: fullname: Smith – year: 2019 ident: ref28 article-title: FedMD: Heterogenous federated learning via model distillation contributor: fullname: Li – year: 2020 ident: ref45 article-title: Federated mutual learning contributor: fullname: Shen – year: 2019 ident: ref13 article-title: Variational federated multi-task learning contributor: fullname: Corinzia – start-page: 3622 volume-title: Proc. Int. Adv. Conf. Neural Inf. Process. Syst. year: 2021 ident: ref40 article-title: QuPed: Quantized personalization via distillation with applications to federated learning contributor: fullname: Ozkara – ident: ref29 doi: 10.1109/ICDE53745.2022.00077 – ident: ref18 doi: 10.1016/j.jpdc.2004.03.020 – ident: ref16 doi: 10.1109/CVPR52688.2022.00992 – year: 2021 ident: ref42 article-title: Adaptive federated optimization publication-title: Proc. Int. Conf. Learn. Representations contributor: fullname: Reddi – start-page: 1273 volume-title: Proc. 26th Int. Conf. Art. Intell. Statist. year: 2017 ident: ref39 article-title: Communication-efficient learning of deep networks from decentralized data contributor: fullname: McMahan – volume-title: Proc. NeurIPS Datasets Benchmarks Track year: 2022 ident: ref10 article-title: pFL-bench: A comprehensive benchmark for personalized federated learning contributor: fullname: Chen – ident: ref30 doi: 10.1609/aaai.v34i04.5895 – start-page: 2089 volume-title: Proc. Int. Conf. Mach. Learn. year: 2021 ident: ref12 article-title: Exploiting shared representations for personalized federated learning contributor: fullname: Collins – start-page: 14068 volume-title: Proc. 34th Int. Conf. Neural Inf. Process. Syst. year: 2020 ident: ref21 article-title: Group knowledge transfer: Federated learning of large CNNs at the edge contributor: fullname: He – start-page: 4423 volume-title: Proc. Int. Conf. Mach. Learn. year: 2021 ident: ref23 article-title: FL-NTK: A neural tangent kernel-based framework for federated learning analysis contributor: fullname: Huang – ident: ref38 doi: 10.1137/1.9781611977172.52 |
SSID | ssj0002511135 |
Score | 2.3105512 |
Snippet | Federated learning is a distributed machine learning approach that allows a single server to collaboratively build machine learning models with multiple... |
SourceID | doaj proquest crossref ieee |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 1 |
SubjectTerms | Benchmark testing Benchmarking Benchmarks Clients Computational modeling Computer vision Customization Data models Datasets Distributed Computing Federated Learning Heterogeneity Machine learning Natural language processing Servers Task analysis Training |
SummonAdditionalLinks | – databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8QwEA66Jy8-V1xf9OBJaG07SR9HV1xEcBV0wVtImomCuIruXvz1TtJ08YHgqQ_6SGeS5vuSzDeMHTlOUGpiqhpzG3MFEKtMYZwqAV5fzPgIuatxcTHhl_fiPgSr-1gYRPSLzzBxu34u37w0czdUduJSEhD-ILKzXKV5G6y1GFBxWDkDEWYus7Q-ub48u01cevAEAHIQ2be-x0v0h5wqv37EvncZrbFxV652UclTMp_ppPn4Idn474Kvs9WAM6PTtmJssCWcbrK1LodDFJr0FouHtH18Vm9PEcHX6KbD5h9oopETmiAsaqKgwvrQZ5PR-d3ZRRxSKMQNT2EWW_qh5SYXttDamkw3ji9UgkCXwrJWDaq8LoSttAE6bjiS4zTPtHFprFKtYZv1pi9T3GERQUOeWVGnWAKRTlUhNsKUBVFIpMfkA3bcGVe-tkoZ0jOMtJbOE9J5QgZPDNjQmX9xoRO59ifIbDK0GZlzhKJELiwo3oiqMqVRRIiwzqyxwAes70z95W2tlQdsv_OmDC3yXdLnlIIDFGL3j9v22AoVkbfjK_usN3ub4wEhjpk-9DXtE6GB0RQ priority: 102 providerName: IEEE |
Title | Benchmark for Personalized Federated Learning |
URI | https://ieeexplore.ieee.org/document/10316561 https://www.proquest.com/docview/2907543365 https://doaj.org/article/24e367e45f3a4c588d7da118e91fdf34 |
Volume | 5 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PS8MwGA2ykxd_TpzO0YMnoVvTL-mPoxuOMZgKOtgtJE2iIE6Z8-LBv90vaSoTD168tLSUpHlfk7zXNu8j5NxpglyhUlUmtTGTALGk0sSJ5OD9xbRfITe7ziZzNl3wxUaqL_dPWG0PXAM3SJmBLDeMW5Cs4kWhcy2RFZuSWm2hdgKlfENMuTHYEWcKPHzGpEk5uJmO7vouV3gfAFLg9MdE5P36Q4KVX6Oyn2rGe2QncMTosr63fbJllgdkt8m_EIXueEjiIe4fn-XqKULqGd02vPrD6GjsTCKQR-ooOKg-tMl8fHU_msQh_UFcsQTWscXBKNUpt5lSVlNVOa5fcCRM0uSlrIxMy4zbQmnA44oZBF0xqrRLQZUoBUektXxZmmMSIa1j1PIyMTmgYJSFMRXXeYbyz2AxaYdcNFiI19rlQnh1kJTCAScccCIA1yFDh9b3hc6g2p_AsIkQNvFX2Dqk7bDeqA2cDxAW3m3AF6E3vQlsTs4ZQMZP_qPuU7KN7WH1i5Quaa1X7-YMqcVa9fxThNvZ51XPrwX8Ap6XyYs |
link.rule.ids | 315,786,790,802,870,2115,27955,27956,55107 |
linkProvider | Directory of Open Access Journals |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB5VcCgXoBTEAqU59ISUkGTsPI4FdbXlsa0ESNwsOx5TCXVBsHvh13fsOIgWIfWUh_JwZuz4-2zPNwBfPCeoDTNVQ6VLhUZMdaEpzbXEoC9mQ4Tc-bSaXImTa3kdg9VDLAwRhcVnlPndMJdv77qFHyo79CkJGH8w2Vnmjj6v-3Ct5yEVj5YLlHHussjbwx8nxxeZTxCeIWKJsvir9wki_TGryqtfcehfxmswHUrWLyu5zRZzk3VP_4g2_nfR12E1Is3ka181PsA7mm3A2pDFIYmN-iOkR7z99Vs_3CYMYJOfAzp_IpuMvdQEo1GbRB3Wm024Gn-7PJ6kMYlC2okc56njX1ppS-kqY5wtTOcZQyMZdmmqW92RLttKusZY5ONOELvOiMJYn8gqNwa3YGl2N6NtSBgcisLJNqcamXbqhqiTtq6YRBI_phzBwWBcdd9rZajAMfJWeU8o7wkVPTGCI2_-5wu9zHU4wWZTsdWoUhBWNQnpUItONo2trWZKRG3hrEMxgk1v6hdv6608gr3Bmyq2yUfFn1NLgVjJnTdu-wzvJ5fnZ-rs-_R0F1a4uKIfbdmDpfnDgj4x_pib_VDr_gDQ09Ro |
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=Benchmark+for+Personalized+Federated+Learning&rft.jtitle=IEEE+open+journal+of+the+Computer+Society&rft.au=Koji+Matsuda&rft.au=Yuya+Sasaki&rft.au=Chuan+Xiao&rft.au=Makoto+Onizuka&rft.date=2024-01-01&rft.pub=IEEE&rft.eissn=2644-1268&rft.volume=5&rft.spage=2&rft.epage=13&rft_id=info:doi/10.1109%2FOJCS.2023.3332351&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_24e367e45f3a4c588d7da118e91fdf34 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2644-1268&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2644-1268&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2644-1268&client=summon |