{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:27:27Z","timestamp":1773930447628,"version":"3.50.1"},"reference-count":27,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":331,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306108"],"award-info":[{"award-number":["62306108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2023AFB042"],"award-info":[{"award-number":["2023AFB042"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>Federated learning (FL) is a novel approach to privacy\u2010preserving machine learning, enabling remote devices to collaborate on model training without exchanging data among clients. However, it faces several challenges, including limited client\u2010side processing capabilities and non\u2010IID data distributions. To address these challenges, we propose a partitioned FL architecture that a large CNN is divided into smaller networks, which train concurrently with other clients. Within a cluster, multiple clients concurrently train the ensemble model. The Jensen\u2013Shannon divergence quantifies the similarity of predictions across submodels. To address discrepancies in model parameters between local and global models caused by data distribution, we propose an ensemble learning method that integrates a penalty term into the local model\u2019s loss calculation, thereby ensuring synchronization. This method amalgamates predictions and losses across multiple submodels, effectively mitigating accuracy loss during the integration process. Extensive experiments with various Dirichlet parameters demonstrate that our system achieves accelerated convergence and enhanced performance on the CIFAR\u201010 and CIFAR\u2010100 image classification tasks while remaining robust to partial participation, diverse datasets, and numerous clients. On the CIFAR\u201010 dataset, our method outperforms FedAvg, FedProx, and SplitFed by 6%\u20138%; in contrast, it outperforms them by 12%\u201318% on CIFAR\u2010100.<\/jats:p>","DOI":"10.1155\/2024\/8860376","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T12:11:50Z","timestamp":1732709510000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Effective Approach for Resource\u2010Constrained Edge Devices in Federated Learning"],"prefix":"10.1155","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8409-0263","authenticated-orcid":false,"given":"Jun","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiusheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6514-1587","authenticated-orcid":false,"given":"Yupeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"crossref","unstructured":"CaropreseL. RugaT. VocaturoE. andZumpanoE. Revealing Brain Tumor With Federated Learning 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) December 2023 Istanbul Turkiye 3868\u20133873 https:\/\/doi.org\/10.1109\/BIBM58861.2023.10385865.","DOI":"10.1109\/BIBM58861.2023.10385865"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_2_10_3_2","article-title":"Federated Optimization in Heterogeneous Networks","author":"Li T.","year":"2020","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_10_4_2","unstructured":"MeiY. GuoP. ZhouM. andPatelV. Resource-Adaptive Federated Learning With All-In-One Neural Composition Advances in Neural Information Processing Systems (NeurIPS\u20192022) December 2022 New Orleans LO 4270\u20134284."},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"ThapaC. ArachchigeP. C. M. CamtepeS. andSunL. SplitFed: When Federated Learning Meets Split Learning Proceedings of the AAAI Conference on Artificial Intelligence 36 no. 8 8485\u20138493 https:\/\/doi.org\/10.1609\/aaai.v36i8.20825.","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"LiuX. DengY. andMahmoodiT. Energy Efficient User Scheduling for Hybrid Split and Federated Learning in Wireless UAV Networks ICC 2022-IEEE International Conference on Communications May 2022 Seoul Korea 1\u20136 https:\/\/doi.org\/10.1109\/ICC45855.2022.9882277.","DOI":"10.1109\/ICC45855.2022.9882277"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3135752"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"AbuadbbaS. KimK. KimM.et al. Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training? Proceedings of the 15th ACM Asia Conference on Computer and Communications Security July 2020 Melbourne Australia.","DOI":"10.1145\/3320269.3384740"},{"key":"e_1_2_10_10_2","volume-title":"Advances in Neural Information Processing Systems","author":"Mei Y.","year":"2022"},{"key":"e_1_2_10_11_2","doi-asserted-by":"crossref","unstructured":"XieS. GirshickR. Doll\u00e1rP. TuZ. andHeK. Aggregated Residual Transformations for Deep Neural Networks IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2022 New Orleans LA 5987\u20135995 https:\/\/doi.org\/10.1109\/CVPR.2017.634 2-s2.0-85043777453.","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_10_12_2","unstructured":"YuJ. YangL. XuN. YangJ. andHuangT. S. Slimmable Neural Networks 2018 https:\/\/arxiv.org\/abs\/1812.08928."},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_18"},{"key":"e_1_2_10_14_2","unstructured":"KondratyukD. TanM. BrownM. andGongB. When Ensembling Smaller Models is More Efficient Than Single Large Models 36th Conference on Neural Information Processing Systems May 2020 New Orleans LA."},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3201602"},{"key":"e_1_2_10_16_2","unstructured":"McMahanH. B. MooreE. RamageD. HampsonS. andArcasB. A. Communication-Efficient Learning of Deep Networks from Decentralized Data 54 Proceedings of the 20th International Conference on Artificial Intelligence and Statistics April 2017 Lauderdale FL PMLR 1273\u20131282."},{"key":"e_1_2_10_17_2","first-page":"5132","article-title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","volume":"119","author":"Karimireddy S. P.","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-05539-7"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"LiQ. HeB. andSongD. Model-Contrastive Federated Learning 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2021 Nashville TN 10708\u201310717 https:\/\/doi.org\/10.1109\/CVPR46437.2021.01057.","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"GaoL. FuH. LiL. ChenY. XuM. andXuC. H. FedDC: Federated Learning With Non-IID Data via Local Drift Decoupling and Correction 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2022 New Orleans LO 10102\u201310111 https:\/\/doi.org\/10.1109\/CVPR52688.2022.00987.","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"e_1_2_10_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3106104"},{"key":"e_1_2_10_22_2","unstructured":"LiX. JiangM. ZhangX. KampM. andDouQ. FedBN: Federated Learning on Non-IID Features via Local Batch Normalization International Conference on Learning Representations May 2021 Vienna Austria."},{"key":"e_1_2_10_23_2","article-title":"Adaptive Federated Optimization","author":"Reddi S.","year":"2021","journal-title":"ICLR"},{"key":"e_1_2_10_24_2","article-title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","author":"Yang H.","year":"2021","journal-title":"ICLR"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"CaropreseL. RugaT. VocaturoE. andZumpanoE. Federated Learning Applications for Breast Cancer 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) December 2023 Istanbul Turkiye 4029\u20134034 https:\/\/doi.org\/10.1109\/BIBM58861.2023.10385394.","DOI":"10.1109\/BIBM58861.2023.10385394"},{"key":"e_1_2_10_26_2","unstructured":"KrizhevskyA. NairV. andHintonG. Cifar-10 (Canadian Institute for Advanced Research) https:\/\/www.cs.toronto.edu\/%7Ekriz\/cifar-10-python.tar.gz."},{"key":"e_1_2_10_27_2","unstructured":"KrizhevskyA. NairV. andHintonG. Cifar-10 (Canadian Institute for Advanced Research) https:\/\/www.cs.toronto.edu\/%7Ekriz\/cifar-100-python.tar.gz."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2024\/8860376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T12:12:08Z","timestamp":1732709528000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2024\/8860376"}},"subtitle":[],"editor":[{"given":"Eugenio","family":"Vocaturo","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1155\/2024\/8860376"],"URL":"https:\/\/doi.org\/10.1155\/2024\/8860376","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2024-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8860376"}}