{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:03:41Z","timestamp":1780020221917,"version":"3.53.1"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471051"],"award-info":[{"award-number":["62471051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.future.2026.108462","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:47:34Z","timestamp":1773002854000},"page":"108462","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Fed3TO: An efficient semi-asynchronous federated learning in bandwidth constrained networks"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4740-6608","authenticated-orcid":false,"given":"Zixuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-383X","authenticated-orcid":false,"given":"Lanlan","family":"Rui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2702-7679","authenticated-orcid":false,"given":"Yijing","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2623-0783","authenticated-orcid":false,"given":"Zihan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0563-6396","authenticated-orcid":false,"given":"Zhipeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7899-539X","authenticated-orcid":false,"given":"Xuesong","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2033-8431","authenticated-orcid":false,"given":"Shaoyong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"13","key":"10.1016\/j.future.2026.108462_bib0001","doi-asserted-by":"crossref","first-page":"23085","DOI":"10.1109\/JIOT.2025.3553163","article-title":"Multirepresentation spatial-temporal graph convolutional networks for network traffic prediction","volume":"12","author":"Yang","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"1","key":"10.1016\/j.future.2026.108462_bib0002","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/TNSM.2023.3314066","article-title":"Feddct: federated learning of large convolutional neural networks on resource-constrained devices using divide and collaborative training","volume":"21","author":"Nguyen","year":"2023","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"issue":"5","key":"10.1016\/j.future.2026.108462_bib0003","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1631\/FITEE.2300122","article-title":"Communication efficiency optimization of federated learning for computing and network convergence of 6G networks","volume":"25","author":"Cai","year":"2024","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"10.1016\/j.future.2026.108462_bib0004","series-title":"Proceedings of the ACM Web Conference 2024 (WWW \u201924)","first-page":"2936","article-title":"Incentive and dynamic client selection for federated unlearning","author":"Lin","year":"2024"},{"issue":"2","key":"10.1016\/j.future.2026.108462_bib0005","doi-asserted-by":"crossref","first-page":"2643","DOI":"10.1109\/TVT.2023.3318080","article-title":"Efficient federated learning in resource-constrained edge intelligence networks using model compression","volume":"73","author":"Chen","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"10.1016\/j.future.2026.108462_bib0006","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TCOMM.2024.3425635","article-title":"Adaptive semi-asynchronous federated learning over wireless networks","volume":"73","author":"Chen","year":"2025","journal-title":"IEEE Trans. Commun."},{"issue":"12","key":"10.1016\/j.future.2026.108462_bib0007","doi-asserted-by":"crossref","first-page":"16280","DOI":"10.1109\/TVT.2023.3298787","article-title":"Semi-asynchronous model design for federated learning in mobile edge networks","volume":"72","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"2","key":"10.1016\/j.future.2026.108462_bib0008","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1109\/TSC.2021.3109910","article-title":"Federated learning with heterogeneity-aware probabilistic synchronous parallel on edge","volume":"15","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"3","key":"10.1016\/j.future.2026.108462_bib0009","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1109\/TPDS.2023.3237752","article-title":"Fedmds an efficient model discrepancy-aware semi-asynchronous clustered federated learning framework","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.future.2026.108462_bib0010","series-title":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications","first-page":"1121","article-title":"A semi-asynchronous decentralized federated learning framework via tree-graph blockchain","author":"Zhang","year":"2024"},{"key":"10.1016\/j.future.2026.108462_bib0011","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia (MM \u201924)","first-page":"2955","article-title":"FedBCGD: communication-efficient accelerated block coordinate gradient descent for federated learning","author":"Liu","year":"2024"},{"key":"10.1016\/j.future.2026.108462_bib0012","series-title":"Federated Quantum Natural Gradient Descent for Quantum Federated Learning","volume":"18","author":"Qi","year":"2024"},{"issue":"11","key":"10.1016\/j.future.2026.108462_bib0013","doi-asserted-by":"crossref","first-page":"2024","DOI":"10.1109\/TMC.2024.3374706","article-title":"Fedpe: adaptive model pruning-expanding for federated learning on mobile devices","volume":"23","author":"Yi","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"1","key":"10.1016\/j.future.2026.108462_bib0014","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TII.2024.3424497","article-title":"Enhancing decentralized federated learning with model pruning and adaptive communication","volume":"21","author":"Xu","year":"2025","journal-title":"IEEE Trans. Ind. Inf."},{"issue":"2","key":"10.1016\/j.future.2026.108462_bib0015","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1109\/TSUSC.2024.3441658","article-title":"Efficient federated learning via adaptive model pruning for internet of vehicles with a constrained latency","volume":"10","author":"Chang","year":"2025","journal-title":"IEEE Trans. Sustainable Comput."},{"key":"10.1016\/j.future.2026.108462_bib0016","first-page":"1","article-title":"Distributed deep reinforcement learning based gradient quantization for federated learning enabled vehicle edge computing","volume":"2024","author":"Zhang","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.future.2026.108462_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2022.102690","article-title":"FedDQ: a communication-efficient federated learning approach for internet of vehicles","volume":"131","author":"Mo","year":"2022","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.future.2026.108462_bib0018","first-page":"191046","article-title":"A hybrid federated learning architecture with online learning and model compression","volume":"12","author":"Odeyomi","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.future.2026.108462_bib0019","doi-asserted-by":"crossref","first-page":"4307","DOI":"10.1109\/OJCOMS.2024.3425531","article-title":"Adaptive sparsification and quantization for enhanced energy efficiency in federated learning","volume":"5","author":"Marnissi","year":"2024","journal-title":"IEEE Open J. Commun. Soc."},{"key":"10.1016\/j.future.2026.108462_bib0020","series-title":"IEEE International Conference on Big Data (Big Data)","first-page":"3873","article-title":"Predicting the computational cost of deep learning models","author":"Justus","year":"2018"},{"issue":"11","key":"10.1016\/j.future.2026.108462_bib0021","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.3390\/a15110391","article-title":"Convolutional neural networks: a roundup and benchmark of their pooling layer variants","volume":"15","author":"Galanis","year":"2022","journal-title":"Algorithms"},{"issue":"2","key":"10.1016\/j.future.2026.108462_bib0022","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1109\/TSC.2024.3517328","article-title":"An adaptive and interpretable congestion control service based on multi-objective reinforcement learning","volume":"18","author":"Liu","year":"2025","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"1","key":"10.1016\/j.future.2026.108462_bib0023","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1109\/TSC.2024.3350050","article-title":"Joint client selection and bandwidth allocation of wireless federated learning by deep reinforcement learning","volume":"17","author":"Mao","year":"2024","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"10","key":"10.1016\/j.future.2026.108462_bib0024","doi-asserted-by":"crossref","first-page":"5992","DOI":"10.1109\/TCOMM.2023.3288591","article-title":"DRL-based adaptive sharding for blockchain-based federated learning","volume":"71","author":"Lin","year":"2023","journal-title":"IEEE Trans. Commun."},{"issue":"6","key":"10.1016\/j.future.2026.108462_bib0025","doi-asserted-by":"crossref","first-page":"3359","DOI":"10.1109\/TSC.2024.3495500","article-title":"Delay-prioritized and reliable task scheduling with long-term load balancing in computing power networks","volume":"17","author":"Xie","year":"2024","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"4","key":"10.1016\/j.future.2026.108462_bib0026","doi-asserted-by":"crossref","first-page":"4731","DOI":"10.1109\/TNSM.2024.3387987","article-title":"Collaborative federated learning for 6G with a deep reinforcement learning-based controlling mechanism: a DDoS attack detection scenario","volume":"21","author":"Kianpisheh","year":"2024","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"issue":"4","key":"10.1016\/j.future.2026.108462_bib0027","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"Lecun","year":"1989","journal-title":"Neural Comput."},{"key":"10.1016\/j.future.2026.108462_bib0028","series-title":"rd IAPR Asian Conference on Pattern Recognition (ACPR)","first-page":"730","article-title":"Very deep convolutional neural network based image classification using small training sample size","author":"Liu","year":"2015"},{"key":"10.1016\/j.future.2026.108462_bib0029","series-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"60","author":"Krizhevsky","year":"2017"},{"key":"10.1016\/j.future.2026.108462_bib0030","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"11","key":"10.1016\/j.future.2026.108462_bib0031","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.future.2026.108462_bib0032","series-title":"International Joint Conference on Neural Networks (IJCNN)","first-page":"2921","article-title":"EMNIST: extending MNIST to handwritten letters","author":"Cohen","year":"2017"},{"key":"10.1016\/j.future.2026.108462_bib0033","series-title":"Technical Report","article-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.future.2026.108462_bib0034","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.future.2026.108462_bib0035","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.future.2023.11.001","article-title":"Adaptive asynchronous federated learning","volume":"152","author":"Lu","year":"2024","journal-title":"Future Gener. Comput. Syst."}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26000968?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26000968?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:39:16Z","timestamp":1780018756000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X26000968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":35,"alternative-id":["S0167739X26000968"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2026.108462","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fed3TO: An efficient semi-asynchronous federated learning in bandwidth constrained networks","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2026.108462","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"108462"}}