{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T09:21:42Z","timestamp":1782552102722,"version":"3.54.5"},"reference-count":57,"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":"Hong Kong RGC","doi-asserted-by":"publisher","award":["TRS T41-603\/20R"],"award-info":[{"award-number":["TRS T41-603\/20R"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ITC ACCESS project"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472050"],"award-info":[{"award-number":["62472050"]}],"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":["62473146"],"award-info":[{"award-number":["62473146"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020762","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2025JJ20070"],"award-info":[{"award-number":["2025JJ20070"]}],"id":[{"id":"10.13039\/501100020762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020762","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ3017"],"award-info":[{"award-number":["2024JJ3017"]}],"id":[{"id":"10.13039\/501100020762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020762","name":"Science and Technology Project of Hunan Provincial Water Resources Department","doi-asserted-by":"publisher","award":["XSKJ2024064-36"],"award-info":[{"award-number":["XSKJ2024064-36"]}],"id":[{"id":"10.13039\/501100020762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020762","name":"New Generation Information Technology Innovation Project 2023","doi-asserted-by":"publisher","award":["2023IT271"],"award-info":[{"award-number":["2023IT271"]}],"id":[{"id":"10.13039\/501100020762","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2025.3607725","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:33:18Z","timestamp":1758043998000},"page":"753-766","source":"Crossref","is-referenced-by-count":1,"title":["DSA: Efficient Data-Plane Memory Scheduler for In-Network Aggregation to Accelerate Distributed Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8216-9683","authenticated-orcid":false,"given":"Jinbin","family":"Hu","sequence":"first","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinming","family":"Xu","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Sai Kung, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5910-0661","authenticated-orcid":false,"given":"Xiaolin","family":"Chen","sequence":"additional","affiliation":[{"name":"Qiongtai Normal University, Haikou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-8738","authenticated-orcid":false,"given":"Jin","family":"Wang","sequence":"additional","affiliation":[{"name":"Sanya Institute, Hunan University of Science and Technology, Sanya, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Sai Kung, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355574"},{"key":"ref2","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. USENIX NSDI","author":"Lao"},{"key":"ref3","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. USENIX NSDI","author":"Sapio"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-024-3342-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3672198.3673800"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645394"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3600061.3603276"},{"key":"ref8","volume-title":"The Source Code of ATP","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446760"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3234200.3234251"},{"key":"ref11","article-title":"BlueConnect: Novel hierarchical all-reduce on multi-tired network for deep learning","volume-title":"Proc. 2nd SysML Conf.","author":"Cho"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/aris.1440370103"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref14","first-page":"829","article-title":"Innetwork aggregation for shared machine learning clusters","volume-title":"Proc. MLSys","author":"Gebara"},{"key":"ref15","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. USENIX NSDI","author":"Gu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3366336"},{"key":"ref17","article-title":"A survey on data plane programming with P4: Fundamentals, advances, and applied research","author":"Hauser","year":"2021","journal-title":"arXiv:2101.10632"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Network simulations with the NS-3 simulator","volume-title":"Proc. ACM SIGCOMM","author":"Henderson"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/02763869.2018.1404391"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672230"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672214"},{"key":"ref23","first-page":"709","article-title":"Characterization of large language model development in the datacenter","volume-title":"Proc. USENIX NSDI","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3088276"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3244794"},{"key":"ref26","first-page":"1801","article-title":"Exploring practical vulnerabilities of machine learning-based wireless systems","volume-title":"Proc. USENIX NSDI","author":"Liu"},{"key":"ref27","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. NIPS","author":"Huang"},{"key":"ref28","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":"ref29","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. USENIX OSDI","author":"Jiang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132764"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31957-3_17"},{"key":"ref32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3414853"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00607"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940562"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3339524"},{"key":"ref37","first-page":"209","article-title":"When should the network be the computer?","volume-title":"Proc. USENIX HotOS","author":"Nelson"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"ref40","first-page":"82","article-title":"PLink: Discovering and exploiting locality for accelerated distributed training on the public cloud","volume-title":"Proc. MLSys","author":"Luo"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098824"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref47","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref48","first-page":"745","article-title":"MegaScale: Scaling large language model training to more than 10,000 GPUs","volume-title":"Proc. USENIX NSDI","author":"jiang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604864"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7471613"},{"key":"ref51","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. USENIX OSDI","author":"Xiao"},{"key":"ref52","first-page":"533","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. USENIX OSDI","author":"Xiao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405857"},{"key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406214"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.11.004"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11165221.pdf?arnumber=11165221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:35Z","timestamp":1773347735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11165221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3607725","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}