Fast-convergent federated learning with class-weighted aggregation
Recently, federated learning has attracted great attention due to its advantage of enabling model training in a distributed manner. Instead of uploading data for centralized training, it allows devices to keep local data private and only send parameters to server. Then the server aggregates local mo...
Saved in:
| Published in | Journal of systems architecture Vol. 117; p. 102125 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.08.2021
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Recently, federated learning has attracted great attention due to its advantage of enabling model training in a distributed manner. Instead of uploading data for centralized training, it allows devices to keep local data private and only send parameters to server. Then the server aggregates local models to derive a global model. In this paper, we study the aggregation problem in federated learning, especially with non-independently and identically distributed data. Since existing scheme may degrade the representative of local models after aggregation, we propose to reallocate weights of local models based on contributions to each class. Then two class-weighted aggregation strategies are developed to improve the communication efficiency in federated learning. Evaluation shows that the proposed schemes reduce 30.49% and 23.59% of communication costs compared with FedAvg. |
|---|---|
| AbstractList | Recently, federated learning has attracted great attention due to its advantage of enabling model training in a distributed manner. Instead of uploading data for centralized training, it allows devices to keep local data private and only send parameters to server. Then the server aggregates local models to derive a global model. In this paper, we study the aggregation problem in federated learning, especially with non-independently and identically distributed data. Since existing scheme may degrade the representative of local models after aggregation, we propose to reallocate weights of local models based on contributions to each class. Then two class-weighted aggregation strategies are developed to improve the communication efficiency in federated learning. Evaluation shows that the proposed schemes reduce 30.49% and 23.59% of communication costs compared with FedAvg. |
| ArticleNumber | 102125 |
| Author | Zhao, Mengying Ma, Zezhong Cai, Xiaojun Jia, Zhiping |
| Author_xml | – sequence: 1 givenname: Zezhong surname: Ma fullname: Ma, Zezhong – sequence: 2 givenname: Mengying orcidid: 0000-0001-7891-5436 surname: Zhao fullname: Zhao, Mengying email: zhaomengying@sdu.edu.cn – sequence: 3 givenname: Xiaojun surname: Cai fullname: Cai, Xiaojun – sequence: 4 givenname: Zhiping surname: Jia fullname: Jia, Zhiping |
| BookMark | eNqFkM9OwzAMhyM0JLbBG3DoC3TEadM_HJBgYoA0iQucI5M6XaaSoiTatLenWzlxgJMtW99P9jdjE9c7Yuwa-AI4FDfbRTgE9HohuIBhJEDIMzaFqszSAgo5GfqsytKyEHDBZiFsOedSgpiyhxWGmOre7ci35GJiqCGPkZqkI_TOujbZ27hJdIchpHuy7ea4xLb11GK0vbtk5wa7QFc_dc7eV49vy-d0_fr0srxfpzrjRUzLvGnKyiDPai6hNBqxro1ETkJjLrEquCnpQ2hpjCSuhaC6bkrMsQCAHLI5y8dc7fsQPBn15e0n-oMCro4e1FaNHtTRgxo9DNjtL0zbeDo8erTdf_DdCNPw2M6SV0Fbcpoa60lH1fT274BvkcV-2Q |
| CitedBy_id | crossref_primary_10_1007_s11227_024_06715_4 crossref_primary_10_1109_TITS_2024_3362909 crossref_primary_10_3390_s23177358 crossref_primary_10_1007_s00607_022_01078_1 crossref_primary_10_1186_s12911_024_02798_4 crossref_primary_10_3390_app14072720 crossref_primary_10_1109_ACCESS_2023_3284976 crossref_primary_10_1016_j_sysarc_2022_102690 crossref_primary_10_3390_jsan13010001 crossref_primary_10_1109_COMST_2024_3399612 crossref_primary_10_1007_s42486_023_00141_w crossref_primary_10_1016_j_dss_2023_114084 crossref_primary_10_1016_j_measurement_2024_116275 crossref_primary_10_1631_FITEE_2400279 crossref_primary_10_1016_j_eswa_2023_122440 crossref_primary_10_3390_e25040606 crossref_primary_10_3390_electronics12091972 crossref_primary_10_3390_diagnostics13203166 crossref_primary_10_1109_TVT_2022_3148872 crossref_primary_10_1109_TNET_2023_3257236 crossref_primary_10_1007_s11704_024_40065_x crossref_primary_10_3390_app13031911 crossref_primary_10_3390_app122312080 crossref_primary_10_1109_TPDS_2023_3240767 crossref_primary_10_3390_sym15071369 crossref_primary_10_3390_sym14020195 |
| Cites_doi | 10.1109/TNNLS.2019.2953131 10.1109/TII.2019.2942190 10.1109/5.726791 10.1109/TNNLS.2019.2944481 10.1109/TIFS.2019.2929409 10.1016/j.ijmedinf.2018.01.007 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier B.V. |
| Copyright_xml | – notice: 2021 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.sysarc.2021.102125 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-6165 |
| ExternalDocumentID | 10_1016_j_sysarc_2021_102125 S138376212100093X |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29L 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BKOMP BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG ROL RPZ RXW SBC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TAE TN5 U5U UHS ~G- AATTM AAXKI AAYWO AAYXX ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c306t-74dd78fa0390517fcaa99f5a0e2ca45a860f7eb2c5ff5e0c22e99d7a4a6111413 |
| IEDL.DBID | .~1 |
| ISSN | 1383-7621 |
| IngestDate | Tue Jul 01 00:29:17 EDT 2025 Thu Apr 24 23:09:23 EDT 2025 Fri Feb 23 02:43:51 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Aggregation Federated learning Non-IID Data |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c306t-74dd78fa0390517fcaa99f5a0e2ca45a860f7eb2c5ff5e0c22e99d7a4a6111413 |
| ORCID | 0000-0001-7891-5436 |
| ParticipantIDs | crossref_primary_10_1016_j_sysarc_2021_102125 crossref_citationtrail_10_1016_j_sysarc_2021_102125 elsevier_sciencedirect_doi_10_1016_j_sysarc_2021_102125 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | August 2021 2021-08-00 |
| PublicationDateYYYYMMDD | 2021-08-01 |
| PublicationDate_xml | – month: 08 year: 2021 text: August 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of systems architecture |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Leroy, Coucke, Lavril, Gisselbrecht, Dureau (b6) 2019 Xiao, Rasul, Vollgraf (b30) 2017 Bagdasaryan, Veit, Hua, Estrin, Shmatikov (b11) 2020; vol. 108 Lalitha, Kilinc, Javidi, Koushanfar (b9) 2019 Konečnỳ, McMahan, Yu, Richtárik, Suresh, Bacon (b22) 2016 Lu, Huang, Dai, Maharjan, Zhang (b8) 2020; 16 Li, Sanjabi, Beirami, Smith (b27) 2019 Krizhevsky, Hinton (b31) 2009 Chen, Sun, Jin (b25) 2020; 31 Bonawitz, Ivanov, Kreuter, Marcedone, McMahan, Patel, Ramage, Segal, Seth (b14) 2017 McMahan, Moore, Ramage, Hampson, y Arcas (b1) 2017; vol. 54 Hard, Rao, Mathews, Ramaswamy, Beaufays, Augenstein, Eichner, Kiddon, Ramage (b4) 2018 Wang, Kaplan, Niu, Li (b19) 2020 Fung, Yoon, Beschastnikh (b28) 2018 Zhao, Li, Lai, Suda, Civin, Chandra (b7) 2018 Yang, Andrew, Eichner, Sun, Li, Kong, Ramage, Beaufays (b5) 2018 Lin, Han, Mao, Wang, Dally (b21) 2017 Mohri, Sivek, Suresh (b26) 2019 Abadi, Chu, Goodfellow, McMahan, Mironov, Talwar, Zhang (b13) 2016 Truex, Baracaldo, Anwar, Steinke, Ludwig, Zhang, Zhou (b15) 2019 Caldas, Konečny, McMahan, Talwalkar (b23) 2018 Li, Huang, Yang, Wang, Zhang (b17) 2019 Brisimi, Chen, Mela, Olshevsky, Paschalidis, Shi (b2) 2018; 112 Nishio, Yonetani (b24) 2019 Melis, Song, De Cristofaro, Shmatikov (b10) 2019 Xu, Li, Liu, Yang, Lin (b12) 2020; 15 Khaled, Mishchenko, Richtárik (b16) 2019 Sheller, Reina, Edwards, Martin, Bakas (b3) 2018 Sattler, Wiedemann, Müller, Samek (b18) 2020; 31 LeCun, Bottou, Bengio, Haffner (b29) 1998; 86 Han, Mao, Dally (b20) 2015 Yang (10.1016/j.sysarc.2021.102125_b5) 2018 Fung (10.1016/j.sysarc.2021.102125_b28) 2018 Lin (10.1016/j.sysarc.2021.102125_b21) 2017 LeCun (10.1016/j.sysarc.2021.102125_b29) 1998; 86 Brisimi (10.1016/j.sysarc.2021.102125_b2) 2018; 112 Abadi (10.1016/j.sysarc.2021.102125_b13) 2016 McMahan (10.1016/j.sysarc.2021.102125_b1) 2017; vol. 54 Bonawitz (10.1016/j.sysarc.2021.102125_b14) 2017 Lalitha (10.1016/j.sysarc.2021.102125_b9) 2019 Mohri (10.1016/j.sysarc.2021.102125_b26) 2019 Sattler (10.1016/j.sysarc.2021.102125_b18) 2020; 31 Zhao (10.1016/j.sysarc.2021.102125_b7) 2018 Truex (10.1016/j.sysarc.2021.102125_b15) 2019 Han (10.1016/j.sysarc.2021.102125_b20) 2015 Khaled (10.1016/j.sysarc.2021.102125_b16) 2019 Caldas (10.1016/j.sysarc.2021.102125_b23) 2018 Li (10.1016/j.sysarc.2021.102125_b27) 2019 Leroy (10.1016/j.sysarc.2021.102125_b6) 2019 Bagdasaryan (10.1016/j.sysarc.2021.102125_b11) 2020; vol. 108 Wang (10.1016/j.sysarc.2021.102125_b19) 2020 Nishio (10.1016/j.sysarc.2021.102125_b24) 2019 Li (10.1016/j.sysarc.2021.102125_b17) 2019 Konečnỳ (10.1016/j.sysarc.2021.102125_b22) 2016 Xu (10.1016/j.sysarc.2021.102125_b12) 2020; 15 Lu (10.1016/j.sysarc.2021.102125_b8) 2020; 16 Melis (10.1016/j.sysarc.2021.102125_b10) 2019 Chen (10.1016/j.sysarc.2021.102125_b25) 2020; 31 Xiao (10.1016/j.sysarc.2021.102125_b30) 2017 Krizhevsky (10.1016/j.sysarc.2021.102125_b31) 2009 Hard (10.1016/j.sysarc.2021.102125_b4) 2018 Sheller (10.1016/j.sysarc.2021.102125_b3) 2018 |
| References_xml | – start-page: 1175 year: 2017 end-page: 1191 ident: b14 article-title: Practical secure aggregation for privacy-preserving machine learning publication-title: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security – year: 2017 ident: b21 article-title: Deep gradient compression: Reducing the communication bandwidth for distributed training – year: 2018 ident: b23 article-title: Expanding the reach of federated learning by reducing client resource requirements – volume: 31 start-page: 3400 year: 2020 end-page: 3413 ident: b18 article-title: Robust and communication-efficient federated learning from non-i.i.d. data publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: b29 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE – year: 2018 ident: b4 article-title: Federated learning for mobile keyboard prediction – year: 2019 ident: b16 article-title: First analysis of local gd on heterogeneous data – year: 2019 ident: b27 article-title: Fair resource allocation in federated learning – year: 2018 ident: b5 article-title: Applied federated learning: Improving google keyboard query suggestions – volume: 112 start-page: 59 year: 2018 end-page: 67 ident: b2 article-title: Federated learning of predictive models from federated electronic health records publication-title: Int. J. Med. Inform. – year: 2018 ident: b7 article-title: Federated learning with non-iid data – year: 2019 ident: b17 article-title: On the convergence of fedavg on non-iid data – start-page: 691 year: 2019 end-page: 706 ident: b10 article-title: Exploiting unintended feature leakage in collaborative learning publication-title: 2019 IEEE Symposium on Security and Privacy (SP) – start-page: 1 year: 2019 end-page: 7 ident: b24 article-title: Client selection for federated learning with heterogeneous resources in mobile edge publication-title: ICC 2019 - 2019 IEEE International Conference on Communications (ICC) – start-page: 1698 year: 2020 end-page: 1707 ident: b19 article-title: Optimizing federated learning on non-iid data with reinforcement learning publication-title: IEEE INFOCOM 2020-IEEE Conference on Computer Communications – volume: vol. 54 start-page: 1273 year: 2017 end-page: 1282 ident: b1 publication-title: Communication-Efficient Learning of Deep Networks from Decentralized Data – start-page: 92 year: 2018 end-page: 104 ident: b3 article-title: Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation publication-title: International MICCAI Brainlesion Workshop – start-page: 1 year: 2019 end-page: 11 ident: b15 article-title: A hybrid approach to privacy-preserving federated learning publication-title: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security – year: 2017 ident: b30 article-title: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms – start-page: 6341 year: 2019 end-page: 6345 ident: b6 article-title: Federated learning for keyword spotting publication-title: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – volume: 31 start-page: 4229 year: 2020 end-page: 4238 ident: b25 article-title: Communication-efficient federated deep learning with layerwise asynchronous model update and temporally weighted aggregation publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 15 start-page: 911 year: 2020 end-page: 926 ident: b12 article-title: Verifynet: Secure and verifiable federated learning publication-title: IEEE Trans. Inf. Forensics Secur. – volume: vol. 108 start-page: 2938 year: 2020 end-page: 2948 ident: b11 article-title: How to backdoor federated learning publication-title: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics – year: 2009 ident: b31 article-title: Learning Multiple Layers of Features from Tiny Images – start-page: 308 year: 2016 end-page: 318 ident: b13 article-title: Deep learning with differential privacy publication-title: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security – year: 2015 ident: b20 article-title: Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding – year: 2019 ident: b9 article-title: Peer to peer federated learning on graphs – year: 2016 ident: b22 article-title: Federated learning: Strategies for improving communication efficiency – year: 2018 ident: b28 article-title: Mitigating sybils in federated learning poisoning – volume: 16 start-page: 4177 year: 2020 end-page: 4186 ident: b8 article-title: Blockchain and federated learning for privacy-preserved data sharing in industrial IoT publication-title: IEEE Trans. Ind. Inf. – year: 2019 ident: b26 article-title: Agnostic federated learning – start-page: 1698 year: 2020 ident: 10.1016/j.sysarc.2021.102125_b19 article-title: Optimizing federated learning on non-iid data with reinforcement learning – volume: 31 start-page: 4229 issue: 10 year: 2020 ident: 10.1016/j.sysarc.2021.102125_b25 article-title: Communication-efficient federated deep learning with layerwise asynchronous model update and temporally weighted aggregation publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2019.2953131 – volume: 16 start-page: 4177 issue: 6 year: 2020 ident: 10.1016/j.sysarc.2021.102125_b8 article-title: Blockchain and federated learning for privacy-preserved data sharing in industrial IoT publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2019.2942190 – volume: vol. 54 start-page: 1273 year: 2017 ident: 10.1016/j.sysarc.2021.102125_b1 – year: 2016 ident: 10.1016/j.sysarc.2021.102125_b22 – year: 2018 ident: 10.1016/j.sysarc.2021.102125_b4 – year: 2019 ident: 10.1016/j.sysarc.2021.102125_b26 – start-page: 308 year: 2016 ident: 10.1016/j.sysarc.2021.102125_b13 article-title: Deep learning with differential privacy – volume: vol. 108 start-page: 2938 year: 2020 ident: 10.1016/j.sysarc.2021.102125_b11 article-title: How to backdoor federated learning – year: 2009 ident: 10.1016/j.sysarc.2021.102125_b31 – year: 2018 ident: 10.1016/j.sysarc.2021.102125_b23 – year: 2017 ident: 10.1016/j.sysarc.2021.102125_b21 – volume: 86 start-page: 2278 issue: 11 year: 1998 ident: 10.1016/j.sysarc.2021.102125_b29 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – year: 2015 ident: 10.1016/j.sysarc.2021.102125_b20 – volume: 31 start-page: 3400 issue: 9 year: 2020 ident: 10.1016/j.sysarc.2021.102125_b18 article-title: Robust and communication-efficient federated learning from non-i.i.d. data publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2019.2944481 – start-page: 1 year: 2019 ident: 10.1016/j.sysarc.2021.102125_b24 article-title: Client selection for federated learning with heterogeneous resources in mobile edge – volume: 15 start-page: 911 year: 2020 ident: 10.1016/j.sysarc.2021.102125_b12 article-title: Verifynet: Secure and verifiable federated learning publication-title: IEEE Trans. Inf. Forensics Secur. doi: 10.1109/TIFS.2019.2929409 – volume: 112 start-page: 59 year: 2018 ident: 10.1016/j.sysarc.2021.102125_b2 article-title: Federated learning of predictive models from federated electronic health records publication-title: Int. J. Med. Inform. doi: 10.1016/j.ijmedinf.2018.01.007 – start-page: 691 year: 2019 ident: 10.1016/j.sysarc.2021.102125_b10 article-title: Exploiting unintended feature leakage in collaborative learning – start-page: 6341 year: 2019 ident: 10.1016/j.sysarc.2021.102125_b6 article-title: Federated learning for keyword spotting – year: 2018 ident: 10.1016/j.sysarc.2021.102125_b5 – year: 2017 ident: 10.1016/j.sysarc.2021.102125_b30 – year: 2019 ident: 10.1016/j.sysarc.2021.102125_b17 – start-page: 1175 year: 2017 ident: 10.1016/j.sysarc.2021.102125_b14 article-title: Practical secure aggregation for privacy-preserving machine learning – year: 2019 ident: 10.1016/j.sysarc.2021.102125_b16 – year: 2018 ident: 10.1016/j.sysarc.2021.102125_b28 – year: 2019 ident: 10.1016/j.sysarc.2021.102125_b9 – start-page: 1 year: 2019 ident: 10.1016/j.sysarc.2021.102125_b15 article-title: A hybrid approach to privacy-preserving federated learning – year: 2019 ident: 10.1016/j.sysarc.2021.102125_b27 – start-page: 92 year: 2018 ident: 10.1016/j.sysarc.2021.102125_b3 article-title: Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation – year: 2018 ident: 10.1016/j.sysarc.2021.102125_b7 |
| SSID | ssj0005512 |
| Score | 2.4332123 |
| Snippet | Recently, federated learning has attracted great attention due to its advantage of enabling model training in a distributed manner. Instead of uploading data... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102125 |
| SubjectTerms | Aggregation Federated learning Non-IID Data |
| Title | Fast-convergent federated learning with class-weighted aggregation |
| URI | https://dx.doi.org/10.1016/j.sysarc.2021.102125 |
| Volume | 117 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB5KvXjxLdZHycHr2jx2s8mxFktV7EULvYXJZrdUpBYbES_-dneSjVQQBY9JZiDMTmZnNt98A3BeoIyVDO0KJDpm3EZhlieRYSrQItAmV341JeJuHI8m_GYqpi0YNL0wBKt0sb-O6VW0dnd6zpq95Xzeuw-ouIpDYsCiunxKHexckpdffKzBPET9x9MKM5Ju2ucqjNfqfWXdyVaJYUAcBgENzP5pe1rbcoY7sOVyRa9fv84utPRiD7abOQye-yz34XKIq5JV-HFqpSw9QwwRNoksPDcUYubReaunKFVmb9VpqH2IM1tsz6qlOYDJ8OphMGJuNgJTNskvmeRFIRODfkQEW9IoxDQ1An0dKuQCk9g30lbNShgjtK_CUKdpIZFjbKOb3bkOob14Xugj8LSPKc8jDLjhPNQxouSoJSotcjRGdiBqTJIpRxxO8yuesgYh9pjVhszIkFltyA6wL61lTZzxh7xsrJ19c4DMxvZfNY__rXkCm3RV4_lOoV2-vOozm2OUebdyoi5s9K9vR-NPRXTTGw |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3JTsMwEB2V9gAXdkRZc-BqNYsdJ8dSUQW6XGil3qKJY1dFqFQ0CPH32InDIiGQuMYeKRpPZnHevAG4ypGHgvv6BCIZEqq9MMmiQBHhSeZJlQm3nBIxGofJlN7N2KwBvboXxsAqre-vfHrpre2TjtVmZ7VYdO49U1yFvmHAMnX5bANahp2KNaHVvR0k40-kB6t-eur9xAjUHXQlzGv9ttYWpQtF3zM0Bp6Zmf1ThPoSdfq7sG3TRadbvdEeNORyH3bqUQyO_TIP4LqP64KUEHLTTVk4ypBE6Dwyd-xciLljrlwdYbJl8lpeiOpFnOt6e16eziFM-zeTXkLseAQidJ5fEE7znEcK3cBwbHElEONYMXSlL5AyjEJXcV04C6YUk67wfRnHOUeKoXZwOngdQXP5tJTH4EgXY5oF6FFFqS9DRE5RchSSZagUb0NQqyQVljvcjLB4TGuQ2ENaKTI1ikwrRbaBfEitKu6MP_bzWtvpNxtItXv_VfLk35KXsJlMRsN0eDsenMKWWangfWfQLJ5f5LlOOYrswprUO43H1cw |
| 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=Fast-convergent+federated+learning+with+class-weighted+aggregation&rft.jtitle=Journal+of+systems+architecture&rft.au=Ma%2C+Zezhong&rft.au=Zhao%2C+Mengying&rft.au=Cai%2C+Xiaojun&rft.au=Jia%2C+Zhiping&rft.date=2021-08-01&rft.pub=Elsevier+B.V&rft.issn=1383-7621&rft.eissn=1873-6165&rft.volume=117&rft_id=info:doi/10.1016%2Fj.sysarc.2021.102125&rft.externalDocID=S138376212100093X |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1383-7621&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1383-7621&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1383-7621&client=summon |