{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:15:53Z","timestamp":1772806553489,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tmc.2024.3414999","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T18:29:03Z","timestamp":1718648943000},"page":"12540-12557","source":"Crossref","is-referenced-by-count":3,"title":["Anchor Model-Based Hybrid Hierarchical Federated Learning With Overlap SGD"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9337-2405","authenticated-orcid":false,"given":"Ousman","family":"Manjang","sequence":"first","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0168-8308","authenticated-orcid":false,"given":"Yanlong","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-7140","authenticated-orcid":false,"given":"Jun","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6797-8148","authenticated-orcid":false,"given":"Jude","family":"Tchaye-Kondi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3277-3887","authenticated-orcid":false,"given":"Liehuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref4","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref5","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref6","article-title":"Federated learning from only unlabeled data with class-conditional-sharing clients","author":"Lu","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3265506"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref9","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"issue":"1","key":"ref10","first-page":"1","article-title":"Robust asynchronous federated learning with time-weighted and stale model aggregation","author":"Miao","year":"2023","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3323282"},{"key":"ref12","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Bonawitz","year":"2019"},{"key":"ref13","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local update SGD","author":"Wang","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01006-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2024.3391329"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00534"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2023.3332770"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3237374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/math10244788"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3189601"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3201310"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3224590"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3294688"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2022.100642"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3153495"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC57700.2023.00173"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3230412"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app132011134"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/WiOpt58741.2023.10349820"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3220809"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3270927"},{"key":"ref33","first-page":"23 034","article-title":"ProgFed: Effective, communication, and computation efficient federated learning by progressive training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref34","first-page":"685","article-title":"Deep learning with elastic averaged SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053834"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3314277"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3200518"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3062721"},{"key":"ref39","article-title":"FedSDD: Scalable and diversity-enhanced distillation for model aggregation in federated learning","author":"Kwan","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3083639"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00054"},{"key":"ref42","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Smith"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3315324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3330171"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040867"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3003744"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3576842.3582377"},{"key":"ref50","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li","year":"2020"},{"key":"ref51","article-title":"FedAT: A communication-efficient federated learning method with asynchronous tiers under Non-IID data","author":"Chai","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3147792"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3238049"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/fi15110352"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3298787"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3166386"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3190512"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20832"},{"key":"ref60","article-title":"Fast convergence of stochastic gradient descent under a strong growth condition","author":"Schmidt","year":"2013"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref62","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref64","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref65","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref66","article-title":"Asynchronous federated optimization","author":"Xie","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3316421"},{"key":"ref68","first-page":"1165","article-title":"How to make the gradients small stochastically: Even faster convex and nonconvex SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Allen-Zhu"},{"key":"ref69","first-page":"2680","article-title":"Natasha 2: Faster non-convex optimization than SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zeyuan"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20832"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10746253\/10559387.pdf?arnumber=10559387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:26:59Z","timestamp":1732667219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10559387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":70,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3414999","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}