{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T17:35:08Z","timestamp":1730223308888,"version":"3.28.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"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":["62132022"],"award-info":[{"award-number":["62132022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1109\/globecom54140.2023.10436745","type":"proceedings-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T19:45:36Z","timestamp":1708976736000},"page":"4140-4145","source":"Crossref","is-referenced-by-count":0,"title":["Performance Modeling and Analysis of Distributed Deep Neural Network Training with Parameter Server"],"prefix":"10.1109","author":[{"given":"Xuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Jiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Dehui","family":"Wei","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Tian","family":"Pan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Tao","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/3285029"},{"key":"ref4","article-title":"Scaling distributed machine learning with in-network aggregation","author":"Sapio","year":"2021","journal-title":"USENIX NSDI 21)"},{"key":"ref5","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on gpu clusters","author":"Zhang","year":"2017","journal-title":"USENIX ATC 17"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/2783258.2783270"},{"key":"ref7","first-page":"463","article-title":"A unified architecture for accelerating distributed {DNN} training in heterogeneous gpu\/cpu clusters","author":"Jiang","year":"2020","journal-title":"USENIX OSDI 20)"},{"key":"ref8","first-page":"652","article-title":"On the utility of gradient compression in distributed training systems","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Agarwa","year":"2022"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TPDS.2021.3052862"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ACCESS.2019.2916550"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/DASC\/PiCom\/DataCom\/CyberSciTec.2018.000-4"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/PADSW.2018.8644932"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/2640087.2644155"},{"year":"2018","author":"Sergeev","journal-title":"Horovod: fast and easy distributed deep learning in tensorflow","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.5555\/2999134.2999257"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"}],"event":{"name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","start":{"date-parts":[[2023,12,4]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,12,8]]}},"container-title":["GLOBECOM 2023 - 2023 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10436708\/10436716\/10436745.pdf?arnumber=10436745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:45:59Z","timestamp":1709253959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10436745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/globecom54140.2023.10436745","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}