{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:43:22Z","timestamp":1770194602069,"version":"3.49.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62432008"],"award-info":[{"award-number":["62432008"]}],"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":["62202300"],"award-info":[{"award-number":["62202300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Research Grants Council (RGC) Research Impact Fund","doi-asserted-by":"publisher","award":["R6021-20"],"award-info":[{"award-number":["R6021-20"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RGC Theme-Based Research Scheme","award":["T43-513\/23N-2"],"award-info":[{"award-number":["T43-513\/23N-2"]}]},{"name":"RGC Collaborative Research Fund","award":["C7004-22G"],"award-info":[{"award-number":["C7004-22G"]}]},{"name":"RGC Collaborative Research Fund","award":["C1029-22G"],"award-info":[{"award-number":["C1029-22G"]}]},{"name":"RGC Collaborative Research Fund","award":["C6015-23G"],"award-info":[{"award-number":["C6015-23G"]}]},{"name":"NSFC\/RGC","award":["CRS_HKUST601\/24"],"award-info":[{"award-number":["CRS_HKUST601\/24"]}]},{"name":"RGC General Research Fund","award":["16207922"],"award-info":[{"award-number":["16207922"]}]},{"name":"RGC General Research Fund","award":["16207423"],"award-info":[{"award-number":["16207423"]}]},{"name":"RGC General Research Fund","award":["16203824"],"award-info":[{"award-number":["16203824"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2025.3644644","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:44:34Z","timestamp":1765997074000},"page":"2997-3012","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Server-Side Communication Bottlenecks in Distributed Learning With Round-Robin Participant Coordination"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5023-3952","authenticated-orcid":false,"given":"Jiayi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9480-5632","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Zuo","family":"Gan","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2990-229X","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2083-9105","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref5","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. NIPS","author":"Sutskever"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737367"},{"key":"ref8","first-page":"21111","article-title":"Virtual homogeneity learning: Defending against data heterogeneity in federated learning","volume-title":"Proc. ICML","author":"Tang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref11","article-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv:1512.01274"},{"key":"ref12","article-title":"Automatic differentiation in PyTorch","author":"Paszke"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref14","article-title":"Revisiting distributed synchronous SGD","author":"Chen","year":"2016","journal-title":"arXiv:1604.00981"},{"key":"ref15","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref16","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. NeurIPS","volume":"25","author":"Dean"},{"key":"ref17","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. NIPS","volume":"2013","author":"Ho"},{"key":"ref18","first-page":"2331","article-title":"Slow learners are fast","volume-title":"Proc. NIPS","author":"Langford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref20","article-title":"Staleness-aware async-SGD for distributed deep learning","author":"Zhang","year":"2015","journal-title":"arXiv:1511.05950"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421299"},{"key":"ref22","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"Proc. OSDI","author":"Narayanan"},{"key":"ref23","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref24","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref25","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Tian","year":"2018","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref26","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Karimireddy"},{"key":"ref27","first-page":"374","article-title":"Towards federated learning at scale: System design","volume":"1","author":"Bonawitz","year":"2019","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps52748.2021.9682059"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838381"},{"key":"ref31","volume-title":"PyTorch","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00054"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563463"},{"key":"ref35","first-page":"814","article-title":"Papaya: Practical, private, and scalable federated learning","volume-title":"Proc. MLSys","author":"Huba"},{"key":"ref36","first-page":"3581","article-title":"Federated learning with buffered asynchronous aggregation","volume-title":"Proc. AISTATS","author":"Nguyen"},{"key":"ref37","article-title":"Practical secure aggregation for federated learning on user-held data","author":"Bonawitz","year":"2016","journal-title":"arXiv:1611.04482"},{"key":"ref38","first-page":"19","article-title":"Oort: Efficient federated learning via guided participant selection","volume-title":"Proc. OSDI","author":"Lai"},{"key":"ref39","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00010"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00099"},{"key":"ref43","article-title":"Federated learning based on dynamic regularization","author":"Acar","year":"2021","journal-title":"arXiv:2111.04263"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054634"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670984"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2994391"},{"key":"ref47","volume-title":"Cisco Devices Only Support Full-Duplex","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2018436.2018442"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312025"},{"key":"ref50","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018","journal-title":"arXiv:1806.00582"},{"key":"ref51","article-title":"On the convergence of fedavg on non-IID data","author":"Li","year":"2019","journal-title":"arXiv:1907.02189"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449847"},{"key":"ref54","article-title":"Three approaches for personalization with applications to federated learning","author":"Mansour","year":"2020","journal-title":"arXiv:2002.10619"},{"key":"ref55","volume-title":"Apache Thrift","year":"2023"},{"key":"ref56","volume-title":"RPyC","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref59","volume-title":"TensorFlow Inception-V3","year":"2023"},{"key":"ref60","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. USENIX NSDI","author":"Hsieh"},{"issue":"140","key":"ref61","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref63","volume-title":"ACL 2016 First Conference on Machine Translation (WMT16)","year":"2016"},{"key":"ref64","first-page":"353","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"Proc. EMNLP Workshop BlackboxNLP, Analyzing Interpreting Neural Netw. NLP","author":"Wang"},{"key":"ref65","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv:1804.03209"},{"key":"ref66","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. ICML","author":"Yurochkin"},{"key":"ref67","first-page":"11814","article-title":"FedScale: Benchmarking model and system performance of federated learning at scale","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lai"},{"key":"ref68","volume-title":"Nethogs","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref70","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref71","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014","journal-title":"arXiv:1412.6115"},{"key":"ref72","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. NIPS","author":"Han"},{"key":"ref73","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX ATC","author":"Zhang"},{"key":"ref74","first-page":"82","article-title":"PLink: Discovering and exploiting datacenter network locality for efficient cloud-based distributed training","volume-title":"Proc. MLSys","author":"Luo"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref76","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume":"1","author":"Jayarajan","year":"2019","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488679"},{"key":"ref79","article-title":"Adaptive periodic averaging: A practical approach to reducing communication in distributed learning","author":"Jiang","year":"2020","journal-title":"arXiv:2007.06134"},{"key":"ref80","first-page":"11082","article-title":"Local SGD with periodic averaging: Tighter analysis and adaptive synchronization","volume-title":"Proc. NeurIPS","author":"Haddadpour"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987554"},{"key":"ref82","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","author":"Jeong","year":"2018","journal-title":"arXiv:1811.11479"},{"key":"ref83","article-title":"Gradient scheduling with global momentum for non-IID data distributed asynchronous training","author":"Li","year":"2019","journal-title":"arXiv:1902.07848"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3606017"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11301868.pdf?arnumber=11301868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:54:28Z","timestamp":1770152068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11301868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3644644","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}