{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T06:41:47Z","timestamp":1769755307148,"version":"3.49.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project","award":["2022YFB2901600"],"award-info":[{"award-number":["2022YFB2901600"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LZ22F010008"],"award-info":[{"award-number":["LZ22F010008"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202406320382"],"award-info":[{"award-number":["202406320382"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tetci.2025.3543765","type":"journal-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T13:48:41Z","timestamp":1741355321000},"page":"3501-3517","source":"Crossref","is-referenced-by-count":1,"title":["NetPlacer+: Model Parallelism Based on Load Balance in Distributed Deep Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0599-8383","authenticated-orcid":false,"given":"Yunqi","family":"Gao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zechao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0594-8998","authenticated-orcid":false,"given":"Bing","family":"Hu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9948-9165","authenticated-orcid":false,"given":"Mahdi Boloursaz","family":"Mashhadi","sequence":"additional","affiliation":[{"name":"5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9680-2811","authenticated-orcid":false,"given":"A-Long","family":"Jin","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7886-5878","authenticated-orcid":false,"given":"Pei","family":"Xiao","sequence":"additional","affiliation":[{"name":"5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"ref2","first-page":"1232","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Dean","year":"2012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796787"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3220224"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040601"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3431572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.05.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3452933"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2935967"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685964"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref15","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014"},{"key":"ref16","first-page":"571","article-title":"Project ADAM: Building an efficient and scalable deep learning training system","volume-title":"Proc. USENIX Symp. Oper. Syst. Des. Implement.","author":"Chilimbi","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750404"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.136.2200562"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3193686"},{"key":"ref20","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref21","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using Megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Narayanan","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"key":"ref23","first-page":"2834","article-title":"On model parallelization and scheduling strategies for distributed machine learning","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Lee","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741115"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901331"},{"key":"ref26","article-title":"Automated tensor model parallelism with overlapped communication for efficient foundation model training","author":"Li","year":"2023"},{"key":"ref27","article-title":"ATP: Adaptive tensor parallelism for foundation models","author":"Cheng","year":"2023"},{"key":"ref28","first-page":"287","article-title":"Collie: Finding performance anomalies in RDMA subsystems","volume-title":"Proc. USENIX Symp. Networked Syst. Des. Implement.","author":"Kong","year":"2022"},{"key":"ref29","first-page":"1","article-title":"SRNIC: A scalable architecture for RDMA NICs","volume-title":"Proc. USENIX Symp. Networked Syst. Des. Implement.","author":"Wang","year":"2023"},{"key":"ref30","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018"},{"key":"ref31","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ML","volume-title":"Proc. MLSys","volume":"2","author":"Wang","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567505"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229029"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3367946"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref36","first-page":"1223","article-title":"More Effective distributed Ml via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Ho","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052862"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2023.103053"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3201531"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3331372"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155446"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488803"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3041219"},{"key":"ref45","article-title":"Distributed deep learning using synchronous stochastic gradient descent","author":"Das","year":"2016"},{"key":"ref46","article-title":"On scale-out deep learning training for cloud and HPC","author":"Sridharan","year":"2018"},{"key":"ref47","article-title":"Multi-GPU training of convnets","volume-title":"Proc. Int. Conf. Learn. Representations Workshop Track","author":"Yadan","year":"2013"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3406420"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3094364"},{"key":"ref50","article-title":"A hierarchical model for device placement","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mirhoseini","year":"2018"},{"key":"ref51","first-page":"2279","article-title":"Exploring hidden dimensions in parallelizing convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2018"},{"key":"ref52","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Jia","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00031"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"8","key":"ref61","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref62","article-title":"Learning multiple layers of features from tiny images","volume-title":"Masters Thesis","author":"Krizhevsky","year":"2009"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1098"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/11177632\/10916805.pdf?arnumber=10916805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:00:08Z","timestamp":1759237208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10916805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":64,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2025.3543765","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}