{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:13:45Z","timestamp":1774311225610,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572304"],"award-info":[{"award-number":["62572304"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202300"],"award-info":[{"award-number":["62202300"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62232011"],"award-info":[{"award-number":["62232011"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpds.2026.3670216","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:54:18Z","timestamp":1772571258000},"page":"1079-1095","source":"Crossref","is-referenced-by-count":0,"title":["Flexible Synchronization Control for Accurate and Efficient Federated Learning"],"prefix":"10.1109","volume":"37","author":[{"given":"Zuo","family":"Gan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9480-5632","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5023-3952","authenticated-orcid":false,"given":"Jiayi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-6507","authenticated-orcid":false,"given":"Yifei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8211-2812","authenticated-orcid":false,"given":"Jieru","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5832-0347","authenticated-orcid":false,"given":"Quan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0461"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01559"},{"key":"ref8","first-page":"10351","article-title":"Towards understanding biased client selection in federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Cho"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref10","first-page":"2921","article-title":"Predicting parameters in deep learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Denil"},{"key":"ref11","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fallah"},{"key":"ref12","article-title":"Balanced multi-modal federated learning via cross-modal infiltration","author":"Fan","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682875"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. 14th USENIX Symp. Networked Syst. Des. Implementation","author":"Hsieh"},{"key":"ref19","article-title":"The Non-IID data quagmire of decentralized machine learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hsieh"},{"key":"ref20","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"ref21","first-page":"814","article-title":"Papaya: Practical, private, and scalable federated learning","volume-title":"Proc. Mach. Learn. Syst.","author":"Huba"},{"key":"ref22","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Jayarajan","year":"2019"},{"key":"ref23","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","author":"Jeong","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref25","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn","year":"2016"},{"key":"ref26","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref27","first-page":"19","article-title":"Oort: Efficient federated learning via guided participant selection","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Lai"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485929"},{"key":"ref31","article-title":"Gradient scheduling with global momentum for non-IID data distributed asynchronous training","author":"Li","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref34","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2018"},{"key":"ref35","article-title":"On the convergence of FedAvg on non-IID data","author":"Li","year":"2019"},{"key":"ref36","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref37","first-page":"5336","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lian"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_18"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228970"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488679"},{"key":"ref42","first-page":"954","article-title":"CMFL: Mitigating communication overhead for federated learning","volume-title":"Proc. IEEE Int. Conf. Distrib. Comput. Syst.","author":"Luping"},{"key":"ref43","first-page":"312","article-title":"L-GreCo: Layerwise-adaptive gradient compression for efficient data-parallel deep learning","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Markov","year":"2024"},{"key":"ref44","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3083316"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref47","article-title":"FedAQ: Communication-efficient federated edge learning via joint uplink and downlink adaptive quantization","author":"Qu","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737367"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054168"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"ref53","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Smith"},{"key":"ref54","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621164"},{"key":"ref56","article-title":"Improving LoRA in privacy-preserving federated learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sun"},{"key":"ref57","article-title":"Well-read students learn better: On the importance of pre-training compact models","author":"Turc","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","first-page":"212","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGS","volume-title":"Proc. 2nd SysML Conf.","author":"Wang"},{"key":"ref60","first-page":"36058","article-title":"CocktailSGD: Fine-tuning foundation models over 500Mbps networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486403"},{"key":"ref63","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.23087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00025"},{"key":"ref66","first-page":"137495","article-title":"Confusion-resistant federated learning via diffusion-based data harmonization on non-IID data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref67","article-title":"Applied federated learning: Improving Google keyboard query suggestions","author":"Yang","year":"2018"},{"key":"ref68","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"ref69","first-page":"1","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-021-00989-x"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3564736"},{"key":"ref72","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11434582\/11419641.pdf?arnumber=11419641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:23:12Z","timestamp":1774308192000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11419641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3670216","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}