{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:20:18Z","timestamp":1773926418070,"version":"3.50.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2208085MF167"],"award-info":[{"award-number":["2208085MF167"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2022NSFSC0543"],"award-info":[{"award-number":["2022NSFSC0543"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20221261"],"award-info":[{"award-number":["BK20221261"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001087"],"award-info":[{"award-number":["62001087"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272428"],"award-info":[{"award-number":["62272428"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171085"],"award-info":[{"award-number":["62171085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871097"],"award-info":[{"award-number":["61871097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20156"],"award-info":[{"award-number":["U20A20156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Networks"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.comnet.2025.111938","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T16:49:22Z","timestamp":1765471762000},"page":"111938","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adaptive computation control and model aggregation for parallel federated learning in heterogeneous edge networks"],"prefix":"10.1016","volume":"275","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2432-3567","authenticated-orcid":false,"given":"Lang","family":"Fan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5278-4677","authenticated-orcid":false,"given":"Zhihao","family":"Zeng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7525-553X","authenticated-orcid":false,"given":"Xiaoning","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3070-686X","authenticated-orcid":false,"given":"Mingjun","family":"Duan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.comnet.2025.111938_bib0001","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MNET.2018.1700202","article-title":"Learning IoT in edge: deep learning for the internet of things with edge computing","volume":"32","author":"Li","year":"2018","journal-title":"IEEE Netw."},{"key":"10.1016\/j.comnet.2025.111938_bib0002","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","article-title":"Edge intelligence: paving the last mile of artificial intelligence with edge computing","volume":"107","author":"Zhou","year":"2019","journal-title":"Proc. IEEE"},{"issue":"6","key":"10.1016\/j.comnet.2025.111938_bib0003","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/MCOM.001.1900461","article-title":"Federated learning for wireless communications: motivation, opportunities and challenges","volume":"58","author":"Niknam","year":"2020","journal-title":"IEEE Commun. Mag"},{"key":"10.1016\/j.comnet.2025.111938_bib0004","series-title":"Proc. Int.","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"Mcmahan","year":"2017"},{"issue":"1\/2","key":"10.1016\/j.comnet.2025.111938_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends Mach. Learn"},{"key":"10.1016\/j.comnet.2025.111938_bib0006","doi-asserted-by":"crossref","first-page":"3877","DOI":"10.1109\/TIFS.2025.3555193","article-title":"Enhanced model poisoning attack and multi-Strategy defense in federated learning","volume":"20","author":"Yang","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Security"},{"issue":"11","key":"10.1016\/j.comnet.2025.111938_bib0007","doi-asserted-by":"crossref","first-page":"3548","DOI":"10.1109\/JSAC.2023.3310094","article-title":"TFL-DT: A trust evaluation scheme for federated learning in digital twin for mobile networks","volume":"41","author":"Guo","year":"2023","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.comnet.2025.111938_bib0008","series-title":"Proc. 20Th Int. Conf","first-page":"509","article-title":"Decentralized collaborative learning of personalized models over networks","author":"Vanhaesebrouck","year":"2017"},{"key":"10.1016\/j.comnet.2025.111938_bib0009","series-title":"Proc. ICC - IEEE Int. Conf. Commun. (ICC)","first-page":"1","article-title":"Client selection for federated learning with heterogeneous resources in mobile edge","author":"Nishio","year":"2019"},{"key":"10.1016\/j.comnet.2025.111938_bib0010","series-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent","author":"Lian","year":"2017"},{"issue":"3","key":"10.1016\/j.comnet.2025.111938_bib0011","doi-asserted-by":"crossref","first-page":"2073","DOI":"10.1109\/TMC.2024.3492916","article-title":"Heterogeneity-Aware cooperative federated edge learning with adaptive computation and communication compression","volume":"24","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Mobile Comput."},{"issue":"6","key":"10.1016\/j.comnet.2025.111938_bib0012","doi-asserted-by":"crossref","first-page":"2640","DOI":"10.1109\/TNET.2023.3257236","article-title":"Optimizing parameter mixing under constrained communications in parallel federated learning","volume":"31","author":"Liu","year":"2023","journal-title":"IEEE\/ACM Trans. Netw."},{"issue":"1","key":"10.1016\/j.comnet.2025.111938_bib0013","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/TMC.2021.3075291","article-title":"Adaptive batch size for federated learning in resource-Constrained edge computing","volume":"22","author":"Ma","year":"2023","journal-title":"IEEE Trans. Mobile Comput."},{"issue":"12","key":"10.1016\/j.comnet.2025.111938_bib0014","doi-asserted-by":"crossref","first-page":"3654","DOI":"10.1109\/JSAC.2021.3118435","article-title":"Fedsa: a semi-Asynchronous federated learning mechanism in heterogeneous edge computing","volume":"39","author":"Ma","year":"2021","journal-title":"IEEE J. Sel. Areas. Commun."},{"issue":"6","key":"10.1016\/j.comnet.2025.111938_bib0015","first-page":"1086","article-title":"ENORM: A framework for edge node resource management","volume":"13","author":"Wang","year":"2020","journal-title":"IEEE Trans. Services Comput."},{"issue":"8","key":"10.1016\/j.comnet.2025.111938_bib0016","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1109\/TPDS.2019.2896894","article-title":"Privacy regulation aware process mapping in geo-distributed cloud data centers","volume":"30","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"8","key":"10.1016\/j.comnet.2025.111938_bib0017","doi-asserted-by":"crossref","first-page":"5168","DOI":"10.1109\/TCOMM.2021.3083316","article-title":"Fast federated learning by balancing communication trade-offs","volume":"69","author":"Nori","year":"2021","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.comnet.2025.111938_bib0018","first-page":"212","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGD","volume":"1","author":"Wang","year":"2019","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.comnet.2025.111938_bib0019","series-title":"Proc. IEEE Conf. Comput. Commun.","first-page":"1","article-title":"Cost-effective federated learning design","author":"Luo","year":"2021"},{"key":"10.1016\/j.comnet.2025.111938_bib0020","series-title":"Proc. Int. Conf.","first-page":"2021","article-title":"Fedpaq: a communication-efficient federated learning method with periodic averaging and quantization","author":"Reisizadeh","year":"2020"},{"key":"10.1016\/j.comnet.2025.111938_bib0021","series-title":"Proc. IEEE Conf. Comput. Commun. (INFOCOM)","first-page":"1","article-title":"P-FedAvg: parallelizing federated learning with theoretical guarantees","author":"Zhong","year":"2021"},{"issue":"1","key":"10.1016\/j.comnet.2025.111938_bib0022","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1109\/TMC.2022.3216837","article-title":"Scalable and low-latency federated learning with cooperative mobile edge networking","volume":"23","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Mobile Comput."},{"issue":"2","key":"10.1016\/j.comnet.2025.111938_bib0023","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1109\/TNSM.2023.3252818","article-title":"Semi-decentralized federated edge learning with data and device heterogeneity","volume":"20","author":"Sun","year":"2023","journal-title":"IEEE Trans. Netw. Service Manag."},{"key":"10.1016\/j.comnet.2025.111938_bib0024","series-title":"Proc. IEEE Int. Joint Conf. Neural Netw","first-page":"1","article-title":"Fedsae: a novel self-Adaptive federated learning framework in heterogeneous systems","author":"Li","year":"2021"},{"key":"10.1016\/j.comnet.2025.111938_bib0025","doi-asserted-by":"crossref","first-page":"9330","DOI":"10.1109\/TVT.2021.3098022","article-title":"Computation offloading for edge-assisted federated learning","volume":"70","author":"Ji","year":"2021","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"10.1016\/j.comnet.2025.111938_bib0026","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1109\/JSAC.2020.3036961","article-title":"Coded computing for low-Latency federated learning over wireless edge networks","volume":"39","author":"Prakash","year":"2021","journal-title":"IEEE J. Sel. Areas Commun."},{"issue":"3","key":"10.1016\/j.comnet.2025.111938_bib0027","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1109\/TMC.2023.3247798","article-title":"Computation and communication efficient federated learning with adaptive model pruning","volume":"23","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Mobile Comput."},{"key":"10.1016\/j.comnet.2025.111938_bib0028","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TSP.2020.3046971","article-title":"UVeQfed: universal vector quantization for federated learning","volume":"69","author":"Shlezinger","year":"2020","journal-title":"IEEE Trans. Signal Process"},{"key":"10.1016\/j.comnet.2025.111938_bib0029","series-title":"Proc. IEEE 40Th Int. Conf. Distrib. Comput. Syst. (ICDCS)","first-page":"300","article-title":"Adaptive gradient sparsification for efficient federated learning: an online learning approach","author":"Han","year":"2020"},{"issue":"10","key":"10.1016\/j.comnet.2025.111938_bib0030","doi-asserted-by":"crossref","first-page":"5675","DOI":"10.1109\/TMC.2022.3186936","article-title":"Adaptive control of local updating and model compression for efficient federated learning","volume":"22","author":"Xu","year":"2023","journal-title":"IEEE Trans. Mobile Comput."},{"key":"10.1016\/j.comnet.2025.111938_bib0031","series-title":"Technical Report","article-title":"Fedzkt: Zero-shot knowledge transfer towards resource-constrained federated learning with heterogeneous ondevice models","author":"Zhang","year":"2021"},{"key":"10.1016\/j.comnet.2025.111938_bib0032","series-title":"Proc. IEEE Wirel.","first-page":"1898","article-title":"Semi-decentralized federated edge learning for fast convergence on non-IID data","author":"Sun","year":"2022"},{"key":"10.1016\/j.comnet.2025.111938_bib0033","series-title":"Proc. AAAI Conf.","article-title":"Demystifying why local aggregation helps: convergence analysis of hierarchical SGD","author":"Wang","year":"2022"},{"issue":"1","key":"10.1016\/j.comnet.2025.111938_bib0034","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TCC.2025.3530681","article-title":"Joint adaptive aggregation and resource allocation for hierarchical federated learning systems based on edge-Cloud collaboration","volume":"13","author":"Su","year":"2025","journal-title":"IEEE Trans. Cloud Comput."},{"key":"10.1016\/j.comnet.2025.111938_bib0035","series-title":"Proc. IEEE Conf. Computing. Commun. (INFOCOM)","first-page":"1","article-title":"Resource-Efficient federated learning with hierarchical aggregation in edge computing","author":"Wang","year":"2021"},{"issue":"7","key":"10.1016\/j.comnet.2025.111938_bib0036","doi-asserted-by":"crossref","first-page":"4084","DOI":"10.1109\/TCOMM.2024.3362143","article-title":"Performance analysis for resource constrained decentralized federated learning over wireless networks","volume":"72","author":"Yan","year":"2024","journal-title":"IEEE Trans. Commun."},{"issue":"12","key":"10.1016\/j.comnet.2025.111938_bib0037","doi-asserted-by":"crossref","first-page":"13834","DOI":"10.1109\/TMC.2024.3437435","article-title":"Two-Layer optimization with utility game and resource control for federated learning in edge networks","volume":"23","author":"Tian","year":"2024","journal-title":"IEEE Trans. Mobile Comput."},{"key":"10.1016\/j.comnet.2025.111938_bib0038","series-title":"Proc. Int. Conf. Learn. Represent","article-title":"Deep gradient compression: reducing the communication bandwidth for distributed training","author":"Lin","year":"2018"},{"key":"10.1016\/j.comnet.2025.111938_bib0039","series-title":"Proc. IEEE Conf. Comput. Commun. (INFOCOM)","first-page":"1387","article-title":"Federated learning over wireless networks: optimization model design and analysis","author":"Tran","year":"2019"},{"issue":"2","key":"10.1016\/j.comnet.2025.111938_bib0040","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1137\/16M1080173","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"Bottou","year":"2018","journal-title":"SIAM Rev"},{"key":"10.1016\/j.comnet.2025.111938_bib0041","series-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","first-page":"1","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","author":"Yang","year":"2021"},{"key":"10.1016\/j.comnet.2025.111938_bib0042","series-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","first-page":"2022","article-title":"Hybrid local SGD for federated learning with heterogeneous communications","author":"Guo","year":"2022"},{"issue":"8","key":"10.1016\/j.comnet.2025.111938_bib0043","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural. Comput."},{"key":"10.1016\/j.comnet.2025.111938_bib0044","first-page":"103","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Proc. Adv. neural Inf. Process Syst."},{"issue":"5","key":"10.1016\/j.comnet.2025.111938_bib0045","doi-asserted-by":"crossref","first-page":"5446","DOI":"10.1109\/TMC.2023.3309497","article-title":"Federated learning with client selection and gradient compression in heterogeneous edge systems","volume":"23","author":"Xu","year":"2024","journal-title":"IEEE Trans. Mobile Comput."},{"issue":"5","key":"10.1016\/j.comnet.2025.111938_bib0046","doi-asserted-by":"crossref","first-page":"2201","DOI":"10.1109\/TNET.2022.3168939","article-title":"Accelerating federated learning via parallel servers: a theoretically guaranteed approach","volume":"30","author":"Liu","year":"2022","journal-title":"IEEE\/ACM Trans. Netw."},{"issue":"1","key":"10.1016\/j.comnet.2025.111938_bib0047","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1109\/TNET.2023.3301972","article-title":"Adaptive block-Wise regularization and knowledge distillation for enhancing federated learning","volume":"32","author":"Liu","year":"2024","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"10.1016\/j.comnet.2025.111938_bib0048","series-title":"Proc. Workshop Federated Learn. Data Privacy Confidentiality","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2019"},{"key":"10.1016\/j.comnet.2025.111938_bib0049","series-title":"Technical Report","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.comnet.2025.111938_bib0050","series-title":"Proc. IEEE Conf. Comput. Commun. (INFOCOM)","first-page":"1698","article-title":"Optimizing federated learning on non-IID data with reinforcement learning","author":"Wang","year":"2020"},{"key":"10.1016\/j.comnet.2025.111938_bib0051","series-title":"Proc. IEEE Conf. Comput. Commun. (INFOCOM)","first-page":"1739","article-title":"Tackling system and statistical heterogeneity for federated learning with adaptive client sampling","author":"Luo","year":"2022"},{"key":"10.1016\/j.comnet.2025.111938_bib0052","series-title":"Proc. IEEE Int. Conf. Commun. (ICC)","first-page":"1","article-title":"Client-edge-cloud hierarchical federated learning","author":"Liu","year":"2020"}],"container-title":["Computer Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S138912862500903X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S138912862500903X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T09:39:56Z","timestamp":1773913196000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S138912862500903X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":52,"alternative-id":["S138912862500903X"],"URL":"https:\/\/doi.org\/10.1016\/j.comnet.2025.111938","relation":{},"ISSN":["1389-1286"],"issn-type":[{"value":"1389-1286","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive computation control and model aggregation for parallel federated learning in heterogeneous edge networks","name":"articletitle","label":"Article Title"},{"value":"Computer Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.comnet.2025.111938","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"111938"}}