{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:11:06Z","timestamp":1770916266093,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["61973324"],"award-info":[{"award-number":["61973324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019318","name":"Guangdong Province Key Laboratory of Computational Science","doi-asserted-by":"publisher","award":["2020B1212060032"],"award-info":[{"award-number":["2020B1212060032"]}],"id":[{"id":"10.13039\/501100019318","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":[[2022,11]]},"DOI":"10.1109\/tnnls.2021.3083655","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T19:45:26Z","timestamp":1622835926000},"page":"6831-6843","source":"Crossref","is-referenced-by-count":17,"title":["Communication-Censored Distributed Stochastic Gradient Descent"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3916-8498","authenticated-orcid":false,"given":"Weiyu","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"given":"Zhaoxian","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3477-1439","authenticated-orcid":false,"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5599-0935","authenticated-orcid":false,"given":"Liping","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-5964","authenticated-orcid":false,"given":"Qing","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Dean"},{"key":"ref2","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Konecn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref3","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref4","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Smith"},{"key":"ref5","article-title":"Expanding the reach of federated learning by reducing client resource requirements","author":"Caldas","year":"2018","journal-title":"arXiv:1812.07210"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2880407"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41589-5_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426691"},{"key":"ref10","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1429274"},{"key":"ref12","first-page":"629","article-title":"Trading computation for communication: Distributed stochastic dual coordinate ascent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref13","first-page":"3068","article-title":"Communication-efficient distributed dual coordinate ascent","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Jaggi"},{"issue":"3","key":"ref14","first-page":"509","article-title":"On an approach to the construction of optimal methods for minimizing smooth convex functions","volume":"24","author":"Nesterov","year":"1988","journal-title":"Mat. Metody Resheniya \u00c8kon. Zadach"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999647"},{"issue":"76","key":"ref16","first-page":"1","article-title":"GADMM: Fast and communication efficient framework for distributed machine learning","volume":"21","author":"Elgabli","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3007634"},{"key":"ref18","article-title":"Decentralization meets quantization","author":"Tang","year":"2018","journal-title":"arXiv:1803.06443"},{"key":"ref19","article-title":"Distributed convex optimization with limited communications","author":"Rao","year":"2018","journal-title":"arXiv:1810.12457"},{"key":"ref20","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Alistarh"},{"key":"ref21","first-page":"559","article-title":"SignSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Intl. Conf. Mach. Learn.","author":"Bernstein"},{"key":"ref22","first-page":"4447","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Stich"},{"key":"ref23","first-page":"5973","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Alistarh"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.787647"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1355-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682575"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2907258"},{"key":"ref29","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Zinkevich"},{"key":"ref30","article-title":"Is local SGD better than minibatch SGD?","author":"Woodworth","year":"2020","journal-title":"arXiv:2002.07839"},{"key":"ref31","first-page":"5050","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","volume-title":"Proc. Adv. Neural Process. Syst.","author":"Chen"},{"key":"ref32","article-title":"Communication-efficient distributed reinforcement learning","author":"Chen","year":"2018","journal-title":"arXiv:1812.03239"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref35","article-title":"On the computation and communication complexity of parallel SGD with dynamic batch sizes for stochastic non-convex optimization","author":"Yu","year":"2019","journal-title":"arXiv:1905.04346"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/16m1080173"},{"key":"ref38","volume-title":"The MNIST Database","author":"LeCun","year":"1998"},{"key":"ref39","volume-title":"UCI machine learning repository","author":"Dua","year":"2017"},{"issue":"4","key":"ref40","first-page":"7","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"Krizhevsky","year":"2012","journal-title":"Univ. Toronto"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511779398"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9931397\/09447173.pdf?arnumber=9447173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:45:56Z","timestamp":1704843956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9447173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":42,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3083655","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}