{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:31:01Z","timestamp":1783791061196,"version":"3.55.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/tbdata.2019.2957478","type":"journal-article","created":{"date-parts":[[2019,12,4]],"date-time":"2019-12-04T22:59:42Z","timestamp":1575500382000},"page":"1-1","source":"Crossref","is-referenced-by-count":31,"title":["GradientFlow: Optimizing Network Performance for Large-Scale Distributed DNN Training"],"prefix":"10.1109","author":[{"given":"Peng","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonggang","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruobing","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wansen","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref3","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref4","article-title":"cuDNN: Efficient primitives for deep learning","author":"Chetlur","year":"2014"},{"key":"ref5","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implementation","author":"Xiao"},{"key":"ref6","article-title":"Large scale deep learning","author":"Dean","year":"2014"},{"key":"ref7","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv preprint arXiv:1512.01274"},{"key":"ref9","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implementation","author":"Abadi"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref11","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","volume-title":"Proc. 11th USENIX Symp. Operating Syst. Design Implementation","author":"Chilimbi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.158"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref17","first-page":"1337","article-title":"Deep learning with COTS HPC systems","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Coates"},{"key":"ref18","article-title":"Highly scalable deep learning training system with mixed-precision: Training ImageNet in four minutes","author":"Jia","year":"2018"},{"key":"ref19","article-title":"Deep image: Scaling up image recognition","author":"Wu","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741965"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3155284.3018769"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0171-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853593"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref28","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref29","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv preprint arXiv:1710.03740"},{"key":"ref30","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref31","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":"ref32","first-page":"693","article-title":"HOGWILD: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. 24th Int. Conf. Neural Inf. Process. Syst.","author":"Recht"},{"key":"ref33","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","author":"Hashemi","year":"2018"},{"key":"ref34","article-title":"Horovod: Fast and easy distributed deep learning in tensorFlow","author":"Sergeev","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2016.0146"},{"key":"ref36","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref38","article-title":"Extremely large minibatch SGD: Training resnet-50 on ImageNet in 15 minutes","author":"Akiba","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/natureI4539"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref42","article-title":"Don\u2019t decay the learning rate, increase the batch size","author":"Smith","year":"2017"},{"key":"ref43","article-title":"Scale out for large minibatch SGD: Residual network training on ImageNet-1k with improved accuracy and reduced time to train","author":"Codreanu","year":"2017"},{"key":"ref44","article-title":"ImageNet\/resnet-50 training in 224 seconds","author":"Mikami","year":"2018"},{"key":"ref45","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref46","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806778"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6687317\/7153538\/08922719.pdf?arnumber=8922719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:26:34Z","timestamp":1704839194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8922719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tbdata.2019.2957478","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}