{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T01:07:57Z","timestamp":1769303277179,"version":"3.49.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013128","name":"Korea Technology and Information Promotion Agency for Small and Medium Enterprises","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013128","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003708","name":"Korean Government","doi-asserted-by":"publisher","award":["S3126610"],"award-info":[{"award-number":["S3126610"]}],"id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003708","name":"Korea Institute of Science and Technology Information","doi-asserted-by":"publisher","award":["K-23-L02-C07-S01"],"award-info":[{"award-number":["K-23-L02-C07-S01"]}],"id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ICT (Information and Communication Technologies) Research and Development Program of Ministry of Science and ICT"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3296609","type":"journal-article","created":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T17:44:11Z","timestamp":1689702251000},"page":"74914-74923","source":"Crossref","is-referenced-by-count":4,"title":["Accelerated Synchronous Model Parallelism Using Cooperative Process for Training Compute-Intensive Models"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0811-5542","authenticated-orcid":false,"given":"Chanhee","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Big Data Science, University of Science and Technology, Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5164-7099","authenticated-orcid":false,"given":"Kyongseok","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Applied AI, University of Science and Technology, Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","author":"he","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref12","first-page":"6543","article-title":"TeraPipe: Token-level pipeline parallelism for training large-scale language models","volume":"139","author":"li","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref14","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref31","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"arXiv 1512 01274"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/app12083972"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3094364"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3083216"},{"key":"ref2","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018","journal-title":"arXiv 1802 05799"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref17","first-page":"269","article-title":"Pipemare: Asynchronous pipeline parallel DNN training","volume":"3","author":"yang","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref16","first-page":"7937","article-title":"Memory-efficient pipeline-parallel DNN training","volume":"139","author":"narayanan","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3070012"},{"key":"ref18","article-title":"XPipe: Efficient pipeline model parallelism for multi-GPU DNN training","author":"guan","year":"2019","journal-title":"arXiv 1911 04610"},{"key":"ref24","article-title":"Low-memory neural network training: A technical report","author":"sohoni","year":"2019","journal-title":"arXiv 1904 10631"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00043"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"shorten","year":"2019","journal-title":"J Big Data"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59719-1_37"},{"key":"ref9","first-page":"1","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume":"32","author":"huang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040601"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00150"},{"key":"ref6","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10185201.pdf?arnumber=10185201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T18:06:49Z","timestamp":1692036409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10185201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3296609","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}