{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:31:52Z","timestamp":1770226312908,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"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":["62072117"],"award-info":[{"award-number":["62072117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2020B010166003"],"award-info":[{"award-number":["2020B010166003"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["22ZR1407000"],"award-info":[{"award-number":["22ZR1407000"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tpds.2023.3250462","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T18:54:04Z","timestamp":1677610444000},"page":"1650-1666","source":"Crossref","is-referenced-by-count":5,"title":["Accelerating Distributed DNN Training via Transport Layer Scheduling"],"prefix":"10.1109","volume":"34","author":[{"given":"Qingyang","family":"Duan","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeqin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4168-3998","authenticated-orcid":false,"given":"Yuedong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoteng","family":"Liu","sequence":"additional","affiliation":[{"name":"2012 Lab, Huawei Technologies Co. Ltd., Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7090-8653","authenticated-orcid":false,"given":"Jun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7466-0384","authenticated-orcid":false,"given":"John C. S.","family":"Lui","sequence":"additional","affiliation":[{"name":"Computer Science & Engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"177","article-title":"Decoding with value networks for neural machine translation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin"},{"key":"ref3","first-page":"4188","article-title":"Gradually updated neural networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qiao"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403341"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3405671.3405810"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000530"},{"key":"ref10","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"ref11","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref12","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Abadi"},{"key":"ref13","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Zhang"},{"key":"ref14","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","volume-title":"Proc. 2nd SysML Conf.","author":"Hashemi"},{"key":"ref15","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. 2nd SysML Conf.","author":"Jayarajan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796752"},{"key":"ref18","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. Des. Implementation","author":"Jiang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref20","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref23","article-title":"Horovod: Fast and easy distributed deep learning in tensorflow","author":"Sergeev","year":"2018"},{"key":"ref24","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Des. Implementation","author":"Weng"},{"key":"ref25","first-page":"533","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao"},{"key":"ref26","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref30","first-page":"578","article-title":"$\\lbrace${TVM $\\rbrace$}: An automated $\\lbrace${ End-to-End$\\rbrace$} optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Chen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737367"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052862"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488803"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3062721"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796820"},{"key":"ref37","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref38","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref39","first-page":"4438","article-title":"Double quantization for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00220"},{"key":"ref41","first-page":"13551","article-title":"ScaleCom: Scalable sparsified gradient compression for communication-efficient distributed training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155269"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2020.2985917"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78615-1_2"},{"key":"ref46","article-title":"Hogwild!: A lock-free approach to parallelizing stochastic gradient descent","author":"Niu","year":"2011"},{"key":"ref47","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796688"},{"key":"ref50","first-page":"241","article-title":"BlueConnect: Novel hierarchical all-reduce on multi-tired network for deep learning","volume-title":"Proc. 2nd SysML Conf.","author":"Cho"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3411029.3411037"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3431307"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155282"},{"key":"ref54","article-title":"Motivating in-network aggregation for distributed deep neural network training","volume-title":"Proc. Workshop Approx. Comput. Across Stack","author":"Luo"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref56","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Sapio"},{"key":"ref57","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. USENIX Conf. Networked Syst. Des. Implementation","author":"Lao"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10075651\/10056319.pdf?arnumber=10056319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:23:44Z","timestamp":1710386624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10056319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":51,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3250462","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":[[2023,5]]}}}