{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:31:13Z","timestamp":1775788273860,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["U24A20245"],"award-info":[{"award-number":["U24A20245"]}],"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":["62132022"],"award-info":[{"award-number":["62132022"]}],"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":["62302524"],"award-info":[{"award-number":["62302524"]}],"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":["624722451"],"award-info":[{"award-number":["624722451"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2024RC1005"],"award-info":[{"award-number":["2024RC1005"]}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ5050"],"award-info":[{"award-number":["2024JJ5050"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ6531"],"award-info":[{"award-number":["2024JJ6531"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/ton.2025.3581112","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:45:04Z","timestamp":1751031904000},"page":"2897-2912","source":"Crossref","is-referenced-by-count":1,"title":["Progress-Aware Transmission Protocol for Efficient In-Network Aggregation in Distributed Machine Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9677-2368","authenticated-orcid":false,"given":"Zhaoyi","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7578-4490","authenticated-orcid":false,"given":"Jiawei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1559-406X","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Changsha University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qile","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4335-8742","authenticated-orcid":false,"given":"Yijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8743-0270","authenticated-orcid":false,"given":"Jingling","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5067-321X","authenticated-orcid":false,"given":"Wanchun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1516-0480","authenticated-orcid":false,"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355636"},{"key":"ref2","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","author":"Fedus","year":"2021","journal-title":"arXiv:2101.03961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355574"},{"key":"ref4","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016","journal-title":"arXiv:1602.02410"},{"key":"ref5","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. 18th USENIX Symp. Networked Syst. Design Implement. (NSDI)","author":"Sapio"},{"key":"ref6","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. 18th USENIX Symp. Networked Syst. Design Implement. (NSDI)","author":"Lao"},{"key":"ref7","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume-title":"Proc. MLSys","volume":"3","author":"Gebara"},{"key":"ref8","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. NIPS","author":"Li"},{"key":"ref9","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref10","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"Proc. USENIX ATC","author":"Jeon"},{"key":"ref11","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":"ref12","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Oper. Syst. Design Implement.","author":"Abadi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2847220.2847223"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2736066"},{"key":"ref15","first-page":"2092","article-title":"\u2019Short-dot\u2019: Computing large linear transforms distributedly using coded short dot products","volume-title":"Proc.  NeurIPS","author":"Dutta"},{"key":"ref16","first-page":"693","article-title":"HOGWILD!: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. NeurIPS","author":"Niu"},{"key":"ref17","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3441039"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref24","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787472"},{"key":"ref26","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Jiang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50743-5_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587436"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3244794"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3387948"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582037"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228956"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575708"},{"key":"ref36","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. MLSys","author":"Jayarajan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11311125\/11053237.pdf?arnumber=11053237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T18:30:38Z","timestamp":1766514638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11053237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":39,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3581112","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}