{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T04:58:54Z","timestamp":1768280334557,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20245"],"award-info":[{"award-number":["U24A20245"]}],"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":["62132022"],"award-info":[{"award-number":["62132022"]}],"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":["U23A20313"],"award-info":[{"award-number":["U23A20313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019081","name":"Science and Technology Innovation Program of Hunan Province","doi-asserted-by":"publisher","award":["2024RC1005"],"award-info":[{"award-number":["2024RC1005"]}],"id":[{"id":"10.13039\/501100019081","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2025.3633713","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:03:15Z","timestamp":1764183795000},"page":"1838-1850","source":"Crossref","is-referenced-by-count":0,"title":["SIM: Accelerating Distributed DNN Training by Exploring Gradient Similarity"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8087-6333","authenticated-orcid":false,"given":"Jin","family":"Ye","sequence":"first","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4335-8742","authenticated-orcid":false,"given":"Yijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7361-343X","authenticated-orcid":false,"given":"Qichen","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7578-4490","authenticated-orcid":false,"given":"Jiawei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1516-0480","authenticated-orcid":false,"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Dean"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01098"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref5","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mirhoseini"},{"key":"ref6","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"Proc. USENIX OSDI","author":"Qiao"},{"key":"ref7","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Jiang"},{"key":"ref8","first-page":"4150","article-title":"PipeTransformer: Automated elastic pipelining for distributed training of large-scale models","volume-title":"Proc. ACM ICML","author":"He"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref11","article-title":"Revisiting distributed synchronous SGD","author":"Chen","year":"2016","journal-title":"arXiv:1604.00981"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3062398"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040601"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref16","first-page":"803","article-title":"Slow and stale gradients can win the race: Error-runtime trade-offs in distributed SGD","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Dutta"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488815"},{"key":"ref18","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ho"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053961"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084806"},{"key":"ref23","first-page":"13551","article-title":"ScaleCom: Scalable sparsified gradient compression for communication-efficient distributed training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref24","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tang"},{"key":"ref25","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. 36th Int. Conf. Machine Learning, (ICML)","author":"Yu"},{"key":"ref26","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref27","first-page":"1","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref30","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NIPS)","author":"Yang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3228733"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref33","first-page":"1","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Stich"},{"key":"ref34","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Alistarh"},{"key":"ref35","first-page":"629","article-title":"Gaia: Geo-Distributed machine learning approaching LAN speeds","volume-title":"Proc. USENIX NSDI","author":"Hsieh"},{"key":"ref36","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Wangni"},{"key":"ref37","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX ATC","author":"Zhang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155269"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11269365.pdf?arnumber=11269365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:19Z","timestamp":1768255219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11269365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3633713","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}