{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T10:11:02Z","timestamp":1775470262292,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Hong Kong Collaborative Research Fund CRF","award":["C5026-18G"],"award-info":[{"award-number":["C5026-18G"]}]},{"name":"Hong Kong General Research Fund GRF","award":["152221\/19E"],"award-info":[{"award-number":["152221\/19E"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572221"],"award-info":[{"award-number":["61572221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1836204"],"award-info":[{"award-number":["U1836204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936108"],"award-info":[{"award-number":["U1936108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2016YFB0800402"],"award-info":[{"award-number":["2016YFB0800402"]}]},{"name":"Major Projects of the National Social Science Foundation","award":["16ZDA092"],"award-info":[{"award-number":["16ZDA092"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832005"],"award-info":[{"award-number":["61832005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872310"],"award-info":[{"award-number":["61872310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RGC Research Impact Fund RIF","award":["R5034-18"],"award-info":[{"award-number":["R5034-18"]}]},{"name":"Hong Kong RGC Research Impact Fund RIF","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Topics Comput."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tetc.2020.3043300","type":"journal-article","created":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T04:14:43Z","timestamp":1607487283000},"page":"1-1","source":"Crossref","is-referenced-by-count":12,"title":["Intermittent Pulling with Local Compensation for Communication-Efficient Distributed Learning"],"prefix":"10.1109","author":[{"given":"Haozhao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoliu","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2020.3006351"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/473"},{"key":"ref5","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294915"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2020.2986238"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2017.2709742"},{"key":"ref10","first-page":"2770","article-title":"Cost aware inference for IoT devices","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Zhu"},{"key":"ref11","first-page":"954","article-title":"CMFL: Mitigating communication overhead for federated learning","volume-title":"Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst.","author":"Luping"},{"key":"ref12","first-page":"5050","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref13","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref14","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2956472"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2010.39"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2739804"},{"key":"ref18","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2018"},{"key":"ref19","first-page":"5973","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/586"},{"key":"ref21","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/300"},{"key":"ref23","first-page":"8045","article-title":"Pipe-SGD: A decentralized pipelined SGD framework for distributed deep net training","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/637"},{"key":"ref25","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate newton-type method","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Shamir"},{"key":"ref26","first-page":"2332","article-title":"GIANT: Globally improved approximate newton method for distributed optimization","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref27","first-page":"797","article-title":"Escaping from saddle points\u2013online stochastic gradient for tensor decomposition","volume-title":"Proc. 28th Conf. Learn. Theory","author":"Ge"},{"key":"ref28","first-page":"1724","article-title":"How to escape saddle points efficiently","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref29","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref31","first-page":"1998","article-title":"Gradient diversity: A key ingredient for scalable distributed learning","volume-title":"Proc. 21st Int. Conf. Artif. Intell. Statist.","author":"Yin"},{"key":"ref32","first-page":"3365","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737632"},{"key":"ref35","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Lian"},{"key":"ref36","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","volume-title":"Proc. 11th USENIX Symp. Operating Syst. Des. Implementation","author":"Chilimbi"},{"key":"ref37","first-page":"1701","article-title":"Asynchronous distributed ADMM for consensus optimization","volume-title":"Proc. 31th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref40","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245516\/6558478\/09286740.pdf?arnumber=9286740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:22:13Z","timestamp":1704842533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9286740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/tetc.2020.3043300","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"value":"2168-6750","type":"electronic"},{"value":"2376-4562","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}