{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:38Z","timestamp":1740165818838,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Consejer\u00eda de Econom\u00eda, Ciencia y Agenda Digital of the Junta de Extremadura"},{"DOI":"10.13039\/501100014181","name":"European Regional Development Fund (ERDF) of the European Union","doi-asserted-by":"publisher","award":["GR21040","GR21099","IB20040"],"award-info":[{"award-number":["GR21040","GR21099","IB20040"]}],"id":[{"id":"10.13039\/501100014181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Spanish Ministerio de Ciencia e Innovacion","doi-asserted-by":"publisher","award":["PID2019-110315RB-I00 (APRISA)"],"award-info":[{"award-number":["PID2019-110315RB-I00 (APRISA)"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DEEP-EST Project"},{"DOI":"10.13039\/100010661","name":"European Union\u2019s Horizon 2020 Research and Innovation Programme","doi-asserted-by":"publisher","award":["754304"],"award-info":[{"award-number":["754304"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3309735","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:03:08Z","timestamp":1695060188000},"page":"17893-17907","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Distributed Neural Network Training Through Node-Based Communications"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1858-9920","authenticated-orcid":false,"given":"Sergio","family":"Moreno-\u00c1lvarez","sequence":"first","affiliation":[{"name":"Departamento de Ingeniería de Sistemas Informáticos y Telemáticos, Escuela Politécnica, Universidad de Extremadura, Cáceres, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1030-3729","authenticated-orcid":false,"given":"Mercedes E.","family":"Paoletti","sequence":"additional","affiliation":[{"name":"Departamento de Tecnología de Computadores y Comunicaciones, Escuela Politécnica, Universidad de Extremadura, Cáceres, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3239-9904","authenticated-orcid":false,"given":"Gabriele","family":"Cavallaro","sequence":"additional","affiliation":[{"name":"Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6701-961X","authenticated-orcid":false,"given":"Juan M.","family":"Haut","sequence":"additional","affiliation":[{"name":"Departamento de Tecnología de Computadores y Comunicaciones, Escuela Politécnica, Universidad de Extremadura, Cáceres, Spain"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3063258"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03200-6"},{"volume-title":"MPI: A Message-passing Interface Standard, Version 3.1; June 4, 2015","year":"2015","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3062398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"A survey on visual transformer","author":"Han","year":"2020","journal-title":"arXiv:2012.12556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","first-page":"64","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Design Appl."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356222"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00220"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3108965"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03638-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1206"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508399"},{"key":"ref21","article-title":"Understanding top-k sparsification in distributed deep learning","author":"Shi","year":"2019","journal-title":"arXiv:1911.08772"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"},{"issue":"12","key":"ref23","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1016\/j.parco.2009.09.001","article-title":"Two-tree algorithms for full bandwidth broadcast, reduction and scan","volume":"35","author":"Sanders","year":"2009","journal-title":"Parallel Comput."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39958-9_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2006.24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-02919-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-018-2724-8"},{"key":"ref29","first-page":"4235","article-title":"Mesh-TensorFlow: Deep learning for supercomputers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shazeer"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00556-1"},{"key":"ref31","first-page":"6281","article-title":"Minibatch vs local SGD for heterogeneous distributed learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Woodworth","year":"2020"},{"key":"ref32","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref33","first-page":"4519","article-title":"Tighter theory for local SGD on identical and heterogeneous data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Khaled"},{"key":"ref34","article-title":"Decoupling the all-reduce primitive for accelerating distributed deep learning","author":"Zhang","year":"2023","journal-title":"arXiv:2302.12445"},{"key":"ref35","first-page":"1","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX Annu. Tech. Conf.","volume":"1","author":"Zhang"},{"key":"ref36","first-page":"1","article-title":"Blueconnect: Novel hierarchical all-reduce on multi-tired network for deep learning","volume-title":"Proc. 2nd SysML Conf.","author":"Cho"},{"key":"ref37","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref38","article-title":"Colossal-AI: A unified deep learning system for large-scale parallel training","author":"Li","year":"2021","journal-title":"arXiv:2110.14883"},{"key":"ref39","first-page":"2991","article-title":"Accelerating asynchronous stochastic gradient descent for neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Bogoychev"},{"key":"ref40","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Wangni"},{"key":"ref41","first-page":"1","article-title":"Communication-efficient distributed SGD with sketching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ivkin"},{"key":"ref42","article-title":"Communication-efficient distributed deep learning: A comprehensive survey","author":"Tang","year":"2020","journal-title":"arXiv:2003.06307"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2020.11.005"},{"key":"ref44","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016","journal-title":"arXiv:1609.04836"},{"key":"ref45","first-page":"1","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Zinkevich"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw.2013.77"},{"issue":"1","key":"ref49","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization (FGVC)","volume":"2","author":"Khosla"},{"article-title":"Caltech-UCSD birds 200","year":"2010","author":"Welinder","key":"ref50"},{"key":"ref51","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1201\/9781351036863-9"},{"key":"ref54","article-title":"Vision transformer pruning","author":"Zhu","year":"2021","journal-title":"arXiv:2104.08500"},{"key":"ref55","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref57","first-page":"1","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhuang"},{"key":"ref58","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref59","article-title":"AngularGrad: A new optimization technique for angular convergence of convolutional neural networks","author":"Roy","year":"2021","journal-title":"arXiv:2105.10190"},{"issue":"8","key":"ref60","first-page":"12","article-title":"Stochastic gradient learning in neural networks","volume":"91","author":"L\u00e9on","year":"1991","journal-title":"Proc. Neuro-Nimes"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10254237.pdf?arnumber=10254237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:03:12Z","timestamp":1733252592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10254237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":60,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3309735","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}