{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T16:02:30Z","timestamp":1740153750578,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","award":["9231333"],"award-info":[{"award-number":["9231333"]}],"id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2022,5,1]]},"DOI":"10.1109\/tsc.2020.2985684","type":"journal-article","created":{"date-parts":[[2020,4,6]],"date-time":"2020-04-06T19:25:32Z","timestamp":1586201132000},"page":"1309-1320","source":"Crossref","is-referenced-by-count":3,"title":["Stanza: Layer Separation for Distributed Training in Deep Learning"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2632-1569","authenticated-orcid":false,"given":"Xiaorui","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9359-9571","authenticated-orcid":false,"given":"Hong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2083-9105","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4175-0097","authenticated-orcid":false,"given":"Yongqiang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920931"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref8","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref10","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref13","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. 23rd Int. Conf. Neural Inf. Process. Syst.","author":"Zinkevich"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"article-title":"PyTorch: Tensors and dynamic neural networks in Python with strong GPU acceleration","year":"2017","author":"Paszke","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/natureI4539"},{"key":"ref17","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Conf. Operating Syst. Des. Implementation","author":"Abadi"},{"article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","year":"2015","author":"Chen","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"article-title":"Performance modeling and evaluation of distributed deep learning frameworks on GPUs","year":"2017","author":"Shi","key":"ref20"},{"article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294915"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1181","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201501008"},{"article-title":"Poseidon: A system architecture for efficient GPU-based deep learning on multiple machines","year":"2015","author":"Zhang","key":"ref25"},{"key":"ref26","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","author":"Dean"},{"article-title":"Deep image: Scaling up image recognition","year":"2015","author":"Wu","key":"ref27"},{"article-title":"Revisiting distributed synchronous SGD","year":"2016","author":"Chen","key":"ref28"},{"article-title":"The CIFAR-10 dataset","year":"2014","author":"Krizhevsky","key":"ref29"},{"article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","year":"2018","author":"Sergeev","key":"ref31"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"Hannun","key":"ref33"},{"article-title":"Using the output embedding to improve language models","year":"2016","author":"Press","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref36","first-page":"II-1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Graves"},{"key":"ref37","first-page":"795","article-title":"Lighter-communication distributed machine learning via sufficient factor broadcasting","volume-title":"Proc. 32nd Conf. Uncertainty Artif. Intell.","author":"Xie"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303957"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806778"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1045","article-title":"Sparse communication for distributed gradient descent","author":"Aji","year":"2017"},{"key":"ref43","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. 14th USENIX Conf. Netw. Syst. Des. Implementation","author":"Hsieh"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4629386\/9799728\/09057737.pdf?arnumber=9057737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:37:21Z","timestamp":1704839841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9057737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,1]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2020.2985684","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"type":"electronic","value":"1939-1374"},{"type":"electronic","value":"2372-0204"}],"subject":[],"published":{"date-parts":[[2022,5,1]]}}}