{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:22:19Z","timestamp":1783095739239,"version":"3.54.6"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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. Netw. Sci. Eng."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tnse.2024.3523320","type":"journal-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T19:18:42Z","timestamp":1735240722000},"page":"1080-1095","source":"Crossref","is-referenced-by-count":3,"title":["A Dynamic Sliding Window Based Tensor Communication Scheduling Framework for Distributed Deep Learning"],"prefix":"10.1109","volume":"12","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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0594-8998","authenticated-orcid":false,"given":"Bing","family":"Hu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-9075","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6062-8639","authenticated-orcid":false,"given":"Rahim","family":"Tafazolli","sequence":"additional","affiliation":[{"name":"5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8941-8080","authenticated-orcid":false,"given":"M\u00e9rouane","family":"Debbah","sequence":"additional","affiliation":[{"name":"KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4188","article-title":"Gradually updated neural networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Qiao","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Amodei","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300364"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/883"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mann","year":"2020"},{"key":"ref7","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"30","author":"Alistarh","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3084104"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref10","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3094364"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref14","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref15","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":"ref16","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","year":"2017"},{"key":"ref17","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Paszke","year":"2019"},{"key":"ref18","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. USENIX Symp. Oper. Syst. Des. Implementation","author":"Abadi","year":"2016"},{"key":"ref19","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"ref20","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. Conf. Machin. Learn. Syst.","volume":"1","author":"Jayarajan","year":"2019"},{"key":"ref21","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","volume-title":"Proc. Conf. Machin. Learn. Syst.","author":"Hashemi","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00054"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488803"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref28","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052862"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796752"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3331372"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"8","key":"ref37","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref38","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Maas","year":"2011"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref40","first-page":"1","article-title":"Naos: Serialization-free RDMA networking in Java","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Taranov","year":"2021"},{"key":"ref41","volume-title":"ZeroMQ: Messaging for Many Applications.","author":"Hintjens","year":"2013"},{"key":"ref42","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ML","volume-title":"Proc. Conf. Machin. Learn. Syst.","author":"Wang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00010"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796820"},{"key":"ref45","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. USENIX Symp. Networked Syst. Des. Implementation","author":"Sapio","year":"2021"},{"key":"ref46","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. USENIX Symp. Networked Syst. Des. Implementation","author":"Lao","year":"2021"},{"key":"ref47","first-page":"593","article-title":"TACCL: Guiding collective algorithm synthesis using communication sketches","volume-title":"Proc. USENIX Symp. Networked Syst. Des. Implementation","author":"Shah","year":"2023"},{"key":"ref48","first-page":"739","article-title":"TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs","volume-title":"Proc. USENIX Symp. Networked Syst. Des. Implementation","author":"Wang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2023.103053"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/10899093\/10816583.pdf?arnumber=10816583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:41:57Z","timestamp":1740422517000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnse.2024.3523320","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}