{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:26:52Z","timestamp":1757312812522,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2019YFB1802600"],"award-info":[{"award-number":["2019YFB1802600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research and Development Program in Key Areas of Guangdong Province","award":["2018B010113001"],"award-info":[{"award-number":["2018B010113001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772305","61672499"],"award-info":[{"award-number":["61772305","61672499"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/tnet.2020.2999377","type":"journal-article","created":{"date-parts":[[2020,6,19]],"date-time":"2020-06-19T20:17:53Z","timestamp":1592597873000},"page":"1752-1764","source":"Crossref","is-referenced-by-count":11,"title":["A Scalable, High-Performance, and Fault-Tolerant Network Architecture for Distributed Machine Learning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2073-8235","authenticated-orcid":false,"given":"Songtao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Dan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6574-8349","authenticated-orcid":false,"given":"Jinkun","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Yanshu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8639-982X","authenticated-orcid":false,"given":"Shutao","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Jianping","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc USENIX (ATC)"},{"key":"ref31","article-title":"ImageNet training in minutes","author":"you","year":"2017","journal-title":"arXiv 1709 05011"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1145\/3123878.3131975"},{"key":"ref10","first-page":"1","article-title":"Project Adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"Proc USENIX (OSDI)"},{"key":"ref11","first-page":"79","article-title":"High-performance distributed ML at scale through parameter server consistency models","author":"dai","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"year":"1993","author":"dongarra","article-title":"A proposal for a user-level, message passing interface in a distributed memory environment","key":"ref12"},{"year":"2017","author":"gibiansky","journal-title":"Bringing HPC Techniques to Deep Learning","key":"ref13"},{"key":"ref14","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1145\/1592568.1592577"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1145\/2934872.2934908"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/1402958.1402968"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref19","first-page":"1","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","author":"hsieh","year":"2017","journal-title":"Proc USENIX (NSDI)"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1177\/1094342005051521"},{"year":"2018","journal-title":"The MNIST Database of Handwritten Digits","key":"ref4"},{"year":"2017","author":"smola","journal-title":"Machine Learning–Progress and Opportunities","key":"ref27"},{"year":"2018","journal-title":"Gloo Project","key":"ref3"},{"key":"ref6","first-page":"1","article-title":"Increasing datacenter network utilisation with GRIN","author":"agache","year":"2015","journal-title":"Proc USENIX (NSDI)"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref5","first-page":"1","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX (OSDI)"},{"key":"ref8","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"arXiv 1512 01274"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1145\/1402958.1402967"},{"year":"2018","journal-title":"Pytorch Website","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/2988450.2988454"},{"year":"2018","journal-title":"Caffe Website","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TNET.2010.2053718"},{"year":"2016","author":"luehr","journal-title":"Fast Multi-GPU Collectives With NCCL","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/2640087.2644155"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagation errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1016\/j.jpdc.2008.09.002"},{"year":"2014","author":"simonyan","journal-title":"arXiv 1409 1556","key":"ref26"},{"key":"ref25","first-page":"696","article-title":"Neurocomputing: Foundations of research","author":"rumelhart","year":"1988","journal-title":"Learning Representations by Backpropagating Error"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/9169972\/09121766.pdf?arnumber=9121766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:42:25Z","timestamp":1651070545000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9121766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":32,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2020.2999377","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"type":"print","value":"1063-6692"},{"type":"electronic","value":"1558-2566"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}