{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:22:58Z","timestamp":1783700578190,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62372426"],"award-info":[{"award-number":["62372426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62102392"],"award-info":[{"award-number":["62102392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"National Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20210121"],"award-info":[{"award-number":["BK20210121"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hefei Municipal Natural Science Foundation","award":["2022013"],"award-info":[{"award-number":["2022013"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2023481"],"award-info":[{"award-number":["2023481"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tnet.2024.3387948","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T17:57:06Z","timestamp":1714413426000},"page":"3437-3452","source":"Crossref","is-referenced-by-count":9,"title":["Accelerating Distributed Training With Collaborative In-Network Aggregation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-1971","authenticated-orcid":false,"given":"Jin","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-4577","authenticated-orcid":false,"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1311-8908","authenticated-orcid":false,"given":"Gongming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuolong","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingchen","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguang","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS57198.2023.10188783"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref6","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. NSDI","author":"Lao"},{"key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405895"},{"key":"ref11","first-page":"279","article-title":"Accelerating distributed reinforcement learning with in-switch computing","volume-title":"Proc. ACM\/IEEE 46th Annu. Int. Symp. Comput. Archit. (ISCA)","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3244794"},{"key":"ref13","volume-title":"Intel Tofino","year":"2021"},{"key":"ref14","volume-title":"32-Port Programmable Switch","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405855"},{"key":"ref16","article-title":"Efficient data-plane memory scheduling for in-network aggregation","author":"Wang","year":"2022","journal-title":"arXiv:2201.06398"},{"key":"ref17","first-page":"51","article-title":"PowerTCP: Pushing the performance limits of datacenter networks","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Design Implement.","author":"Addanki"},{"key":"ref18","article-title":"Alpa: Automating inter- and intra-operator parallelism for distributed deep learning","author":"Zheng","year":"2022","journal-title":"arXiv:2201.12023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2582748"},{"key":"ref20","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Conf. Operating Syst. Design Implement.","author":"Xiao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053834"},{"key":"ref23","first-page":"212","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGD","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Wang"},{"key":"ref24","article-title":"Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms","author":"Wang","year":"2018","journal-title":"arXiv:1808.07576"},{"key":"ref25","first-page":"1","article-title":"Pipe-SGD: A decentralized pipelined SGD framework for distributed deep net training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref26","article-title":"Communication-efficient distributed deep learning: A comprehensive survey","author":"Tang","year":"2020","journal-title":"arXiv:2003.06307"},{"key":"ref27","first-page":"1","article-title":"DETOX: A redundancy-based framework for faster and more robust gradient aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rajput"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref29","first-page":"1","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen"},{"key":"ref30","first-page":"1","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Vogels"},{"key":"ref31","first-page":"1","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Zinkevich"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582037"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355574"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587436"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2018.8549549"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.2985037"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3258982"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3470567"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3357874"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2922285"},{"key":"ref44","volume-title":"Intel Tofino 2","year":"2022"},{"key":"ref45","first-page":"1","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref46","volume-title":"Pulp","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2853587"},{"key":"ref48","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1402946.1402967"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1198"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.106.682658"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7641-3_9"},{"key":"ref53","first-page":"803","article-title":"Slow and stale gradients can win the race: Error-runtime trade-offs in distributed SGD","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Dutta"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3186936"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/infocom42981.2021.9488815"},{"key":"ref56","volume-title":"IFTOP","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155282"},{"key":"ref58","volume-title":"CIFAR-100 (Canadian Institute for Advanced Research)","author":"Krizhevsky","year":"2024"},{"key":"ref59","article-title":"DenseNet: Implementing efficient ConvNet descriptor pyramids","author":"Iandola","year":"2014","journal-title":"arXiv:1404.1869"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934893"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787507"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","volume-title":"An Instant Virtual Network on Your Laptop","year":"2024"},{"key":"ref64","volume-title":"Behavioral Model Version 2 (BMV2)","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3132018"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10640200\/10509728.pdf?arnumber=10509728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T04:36:11Z","timestamp":1725078971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10509728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":65,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2024.3387948","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}