{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:49:15Z","timestamp":1783183755405,"version":"3.54.6"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42275157"],"award-info":[{"award-number":["42275157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Auton. Adapt. Syst."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>\n                    The advancement of mobile multimedia communications, 5G, and Internet of Things (IoT) has led to the widespread use of edge devices, including sensors, smartphones, and wearables. This has generated in a large amount of distributed data, leading to new prospects for deep learning. However, this data is confined within data silos and contains sensitive information, making it difficult to be processed in a centralized manner, particularly under stringent data privacy regulations. Federated learning (FL) offers a solution by enabling collaborative learning while ensuring privacy. Nonetheless, data and device heterogeneity complicate FL implementation. This research presents a specialized FL algorithm for heterogeneous edge computing. It integrates a lightweight grouping strategy for homogeneous devices, a scheduling algorithm within groups, and a Split Learning (SL) approach. These contributions enhance model accuracy and training speed, alleviate the burden on resource-constrained devices, and strengthen privacy. Experimental results demonstrate that the GSFL outperforms FedAvg and SplitFed by 6.53\u00d7 and 1.18\u00d7. Under experimental conditions with\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\alpha=0.05\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , representing a highly heterogeneous data distribution typical of extreme Non-IID scenarios, GSFL showed better accuracy compared to FedAvg by 10.64%, HACCS by 4.53%, and Cluster-HSFL by 1.16%. GSFL effectively balances privacy protection and computational efficiency for real-world applications in mobile multimedia communications.\n                  <\/jats:p>","DOI":"10.1145\/3725221","type":"journal-article","created":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T11:22:20Z","timestamp":1742469740000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["GSFL: A Privacy-Preserving Grouping-Split Federated Learning Approach in Resource-Constrained Edge Computing Scenarios"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8485-3582","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"first","affiliation":[{"name":"Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services, Nanjing, China and School of Software, Nanjing University of Information Science and Technology, Nanjing,\u00a0China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0320-8718","authenticated-orcid":false,"given":"Zhilu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Information Science and\u00a0Technology,\u00a0Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3488-4679","authenticated-orcid":false,"given":"Xiaokang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Business Data Science, Kansai University, Suita, Japan and RIKEN\u00a0Center\u00a0for Advanced Intelligence Project, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3011-3113","authenticated-orcid":false,"given":"Yonghong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Nanjing University of Information Science and Technology, Nanjing,\u00a0China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7612-9981","authenticated-orcid":false,"given":"Xiaodong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2872-4801","authenticated-orcid":false,"given":"Haiyang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Software, Nanjing University of Information Science and Technology, Nanjing,\u00a0China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207469"},{"key":"e_1_3_1_3_2","unstructured":"Luca Corinzia Ami Beuret and Joachim M. Buhmann. 2019. Variational federated multi-task learning. arXiv:1906.06268. Retrieved from https:\/\/arxiv.org\/abs\/1906.06268"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS60048.2023.00084"},{"key":"e_1_3_1_6_2","unstructured":"Yuyang Deng Mohammad Mahdi Kamani and Mehrdad Mahdavi. 2020. Adaptive personalized federated learning. arXiv:2003.13461. Retrieved from https:\/\/arxiv.org\/abs\/2003.13461"},{"key":"e_1_3_1_7_2","volume-title":"9th International Conference on Learning Representations","author":"Diao Enmao","year":"2021","unstructured":"Enmao Diao, Jie Ding, and Vahid Tarokh. 2021. HeteroFL: Computation and communication efficient federated learning for heterogeneous clients. In 9th International Conference on Learning Representations. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=TNkPBBYFkXg"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00042"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3247554"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJAHUC.2023.127781"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3339633"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3309321"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3192506"},{"key":"e_1_3_1_14_2","unstructured":"Filip Hanzely and Peter Richt\u00e1rik. 2020. Federated learning of a mixture of global and local models. arXiv:2002.05516. Retrieved from https:\/\/arxiv.org\/abs\/2002.05516"},{"key":"e_1_3_1_15_2","unstructured":"Chaoyang He Murali Annavaram and Salman Avestimehr. 2020. Group knowledge transfer: Federated learning of large CNNs at the edge. In Advances in Neural Information Processing Systems 33 14068\u201314080. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/a1d4c20b182ad7137ab3606f0e3fc8a4-Paper.pdf"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC58020.2023.10183145"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3181848"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3315673"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3229516"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00386"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3321679"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449847"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-022-01664-x"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3301972"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3342873"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3244336"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSMC.2022.3216943"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2023.3283509"},{"issue":"12","key":"e_1_3_1_30_2","first-page":"2515","article-title":"Edge-based model cleaning and device clustering in federated learning","volume":"44","author":"Liu Yan","year":"2021","unstructured":"Yan Liu, Tian Wang, Shaoliang Peng, Guojun Wang, and Weijia Jia. 2021. Edge-based model cleaning and device clustering in federated learning. Chinese Journal of Computers 44, 12 (2021), 2515\u20132528. Retrieved from http:\/\/cjc.ict.ac.cn\/online\/onlinepaper\/liuy-20211217120533.pdf","journal-title":"Chinese Journal of Computers"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796935"},{"key":"e_1_3_1_32_2","first-page":"1273","volume-title":"20th International Conference on Artificial Intelligence and Statistics","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In 20th International Conference on Artificial Intelligence and Statistics. PMLR, 1273\u20131282. Retrieved from https:\/\/proceedings.mlr.press\/v54\/mcmahan17a.html"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3302016"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3596907"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3244243"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3309633"},{"key":"e_1_3_1_39_2","first-page":"4424","article-title":"Federated multi-task learning","volume":"30","author":"Smith Virginia","year":"2017","unstructured":"Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi, and Ameet S. Talwalkar. 2017. Federated multi-task learning. In Advances in Neural Information Processing Systems 30, 4424\u20134434. DOI: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/6211080fa89981f66b1a0c9d55c61d0f-Paper.pdf","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000372"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00100"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-021-00988-y"},{"key":"e_1_3_1_46_2","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747. Retrieved from https:\/\/arxiv.org\/abs\/1708.07747"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3317632"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625558"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3277878"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228953"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366506"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2023.9010058"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC57788.2023.10233408"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.03.020"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120217"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3362058"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.004.2200381"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102182"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3345431"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3259431"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310046"}],"container-title":["ACM Transactions on Autonomous and Adaptive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T13:29:13Z","timestamp":1764163753000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725221"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3725221"],"URL":"https:\/\/doi.org\/10.1145\/3725221","relation":{},"ISSN":["1556-4665","1556-4703"],"issn-type":[{"value":"1556-4665","type":"print"},{"value":"1556-4703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,26]]},"assertion":[{"value":"2024-02-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}