{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:19:54Z","timestamp":1759331994351,"version":"3.37.3"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42001398"],"award-info":[{"award-number":["42001398"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Chongqing Natural Science Foundation","doi-asserted-by":"crossref","award":["0635"],"award-info":[{"award-number":["0635"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M693929"],"award-info":[{"award-number":["2021M693929"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Research Project of Chongqing Education Commission","award":["KJQN201900612"],"award-info":[{"award-number":["KJQN201900612"]}]},{"name":"Open Fund of State Laboratory of Information Engineering in Surveying"},{"name":"Mapping and Remote Sensing, Wuhan University","award":["20S02"],"award-info":[{"award-number":["20S02"]}]},{"DOI":"10.13039\/501100004502","name":"Chongqing University of Posts and Telecommunications","doi-asserted-by":"publisher","award":["A2019-302"],"award-info":[{"award-number":["A2019-302"]}],"id":[{"id":"10.13039\/501100004502","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Federated learning (FL) can learn a shared global model across multiple client devices without breaching privacy requirements. But an essential challenge is that devices in FL usually have limited network bandwidth, resulting in inefficient communication as an important bottleneck for FL implementation. Current studies try to overcome this shortcoming by compressing the number of model update bits uploaded by every client. But they did not explore the underlying reason why redundant parameters are generated. In this paper, we propose Corset-Based Federated Learning framework (CBFL) \u2014a novel FL communication framework from the perspective of redundancy data. Instead of training full datasets on a regular network model, CBFL trains a much smaller evolution network model on extracted corset, which intrinsically reduces the overall transmission bits and obtains efficient computation while maintaining a desirable model accuracy. In CBFL, a novel Fedcorset construction algorithm at selected clients and a further distributed model evolution scheme to fit the constructed corset are included. The training model size is dynamically adapted to the corset, either removing a fraction of unimportant or adding important connections at each communication iteration. Experimental results show that CBFL transfers about 13% of communication bits and saves around 56% computing time while having only 2% destination in model accuracy.<\/jats:p>","DOI":"10.1093\/comjnl\/bxac062","type":"journal-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T11:22:05Z","timestamp":1651058525000},"page":"2077-2101","source":"Crossref","is-referenced-by-count":2,"title":["Federated Learning Communication-Efficiency Framework via Corset Construction"],"prefix":"10.1093","volume":"66","author":[{"given":"Kaiju","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Tourism Multisource Data Perception and Decision, Ministry of Culture and Tourism, College of Computer Science and Technology, Chongqing University of Posts and Telecommunications , Chongqing, 400065, P.R. China"},{"name":"Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, College of Computer Science, Chongqing University , Chongqing, 400044, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Tourism Multisource Data Perception and Decision, Ministry of Culture and Tourism, College of Computer Science and Technology, Chongqing University of Posts and Telecommunications , Chongqing, 400065, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,5,20]]},"reference":[{"key":"2023091720461171900_ref1","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":"He","year":"2018","journal-title":"IEEE Netw."},{"key":"2023091720461171900_ref2","first-page":"1","article-title":"An efficient spam detection technique for IoT devices using machine learning","volume":"99","author":"Makkar","year":"2020","journal-title":"IEEE T. Ind Inform."},{"key":"2023091720461171900_ref3","first-page":"1","article-title":"Edge cloud server deployment with transmission power control through machine learning for 6G","volume":"99","author":"Rodrigues","year":"2019","journal-title":"IEEE T. Emerg. Top. Com."},{"key":"2023091720461171900_ref4","first-page":"1273","volume-title":"Int. Conf. on Artificial Intelligence and Statistics","author":"McMahan","year":"2017"},{"article-title":"Model pruning enables efficient federated learning on edge devices","year":"2019","author":"Jiang","key":"2023091720461171900_ref5"},{"key":"2023091720461171900_ref6","first-page":"3400","article-title":"Robust and communication-efficient federated learning from non-IID data","volume":"9","author":"Sattler","year":"2019","journal-title":"IEEE T. Neur. Net. Lear."},{"key":"2023091720461171900_ref7","first-page":"3973","volume-title":"Int. Conf. on Machine Learning","author":"Hamer","year":"2020"},{"article-title":"Federated learning: strategies for improving communication efficiency","year":"2016","author":"Kone\u010dny","key":"2023091720461171900_ref8"},{"key":"2023091720461171900_ref9","first-page":"1310","article-title":"Multi-objective evolutionary federated learning","volume":"31","author":"Zhu","year":"2020","journal-title":"IEEE T. Neur. Net. Lear."},{"key":"2023091720461171900_ref10","first-page":"1","volume-title":"Int. Conf. on Communications (ICC)","author":"Sun","year":"2020"},{"key":"2023091720461171900_ref11","first-page":"50","article-title":"Federated learning: challenges, methods, and future directions","volume":"3","author":"Li","year":"2020","journal-title":"IEEE Signal. Proc. Mag."},{"key":"2023091720461171900_ref12","first-page":"1","volume-title":"Int. Conf. on Communications (ICC)","author":"Lian","year":"2021"},{"key":"2023091720461171900_ref13","first-page":"1488","volume-title":"Int. Conf. on Speech Communication Association","author":"Strom","year":"2015"},{"key":"2023091720461171900_ref14","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1045","volume-title":"Sparse communication for distributed gradient descent","author":"Aji","year":"2017"},{"key":"2023091720461171900_ref15","first-page":"954","volume-title":"Int. Conf. on Distributed Computing Systems (ICDCS)","author":"Wang","year":"2019"},{"key":"2023091720461171900_ref16","first-page":"629","volume-title":"Int. Conf. on Networked Systems Design and Implementation (NSDI 17)","author":"Hsieh","year":"2018"},{"article-title":"Lotteryfl: personalized and communication-efficient federated learning with lottery ticket hypothesis on non-IID datasets","year":"2020","author":"Li","key":"2023091720461171900_ref17"},{"article-title":"Deep gradient compression: reducing the communication bandwidth for distributed training","year":"2018","author":"Lin","key":"2023091720461171900_ref18"},{"key":"2023091720461171900_ref19","doi-asserted-by":"crossref","first-page":"11053","DOI":"10.1109\/JIOT.2020.2994596","article-title":"Toward communication-efficient federated learning in the internet of things with edge computing","volume":"11","author":"Sun","year":"2020","journal-title":"IEEE Internet Things"},{"key":"2023091720461171900_ref20","first-page":"1","volume-title":"Int. Conf. on Hot Topics in Edge Computing (HotEdge 18)","author":"Tao","year":"2018"},{"key":"2023091720461171900_ref21","first-page":"560","volume-title":"Int. Conf. on on Machine Learning","author":"Bernstein","year":"2018"},{"key":"2023091720461171900_ref22","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1109\/TIFS.2020.3043139","article-title":"VeriFL: communication-efficient and fast verifiable aggregation for federated learning","volume":"16","author":"Guo","year":"2020","journal-title":"IEEE T. Inf. Foren. Sec."},{"key":"2023091720461171900_ref23","first-page":"2021","volume-title":"Int. Conf. on Artificial Intelligence and Statistics (AISTATS)","author":"Reisizadeh","year":"2020"},{"article-title":"Federated learning with quantized global model updates","year":"2020","author":"Amiri","key":"2023091720461171900_ref24"},{"article-title":"Hyper-sphere quantization: communication-efficient SGD for federated learning","year":"2019","author":"Dai","key":"2023091720461171900_ref25"},{"key":"2023091720461171900_ref26","first-page":"5325","volume-title":"Int. Conf. on Machine Learning","author":"Wu","year":"2018"},{"article-title":"Terngrad: ternary gradients to reduce communication in distributed deep learning","year":"2018","author":"Wen","key":"2023091720461171900_ref27"},{"key":"2023091720461171900_ref28","first-page":"1162","article-title":"Ternary compression for communication-efficient federated learning","volume":"33","author":"Xu","year":"2022","journal-title":"IEEE T. Neur. Net. Lear."},{"key":"2023091720461171900_ref29","first-page":"250","volume-title":"Int. Conf. on Theory of Computing","author":"B\u0101doiu","year":"2002"},{"article-title":"Coresets for scalable Bayesian logistic regression","year":"2016","author":"Huggins","key":"2023091720461171900_ref30"},{"first-page":"698","volume-title":"Int. Conf. on Machine Learning","author":"Campbell","key":"2023091720461171900_ref31"},{"key":"2023091720461171900_ref32","first-page":"1","volume-title":"Int. Conf. on Signal Processing Advances in Wireless Communications (SPAWC)","author":"Fan","year":"2018"},{"key":"2023091720461171900_ref33","doi-asserted-by":"crossref","first-page":"2400","DOI":"10.1109\/JSAC.2020.3000373","article-title":"Robust coreset construction for distributed machine learning","volume":"10","author":"Lu","year":"2020","journal-title":"IEEE J. Sel. Area. Comm."},{"key":"2023091720461171900_ref34","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/5.784219","article-title":"Evolving artificial neural networks","volume":"87","author":"Yao","year":"1999","journal-title":"P. IEEE."},{"key":"2023091720461171900_ref35","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1162\/106365602320169811","article-title":"Evolving neural networks through augmenting topologies","volume":"2","author":"Stanley","year":"2002","journal-title":"Evol. Comput."},{"key":"2023091720461171900_ref36","first-page":"410","volume-title":"Int. Conf. on Modeling and Simulation","author":"Fekia\u010d","year":"2011"},{"key":"2023091720461171900_ref37","first-page":"1","article-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science","volume":"1","author":"Mocanu","year":"2018","journal-title":"Nat. Commun."},{"key":"2023091720461171900_ref38","first-page":"10713","volume-title":"Int. Conf. on Computer Vision and Pattern Recognition","author":"Li","year":"2021"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/9\/2077\/51643617\/bxac062.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/9\/2077\/51643617\/bxac062.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T21:10:03Z","timestamp":1694985003000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/66\/9\/2077\/6589512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,20]]},"references-count":38,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5,20]]},"published-print":{"date-parts":[[2023,9,18]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxac062","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published-other":{"date-parts":[[2023,9]]},"published":{"date-parts":[[2022,5,20]]}}}