{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:02:03Z","timestamp":1766138523013,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tc.2023.3343110","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T19:28:23Z","timestamp":1702927703000},"page":"801-814","source":"Crossref","is-referenced-by-count":3,"title":["GreedW: A Flexible and Efficient Decentralized Framework for Distributed Machine Learning"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7223-8849","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, the Engineering Research Center of Software\/Hardware Co-Design Technology and Application (MoE), Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5164-306X","authenticated-orcid":false,"given":"Xin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, the Engineering Research Center of Software\/Hardware Co-Design Technology and Application (MoE), Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7476-4079","authenticated-orcid":false,"given":"Qin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, the Engineering Research Center of Software\/Hardware Co-Design Technology and Application (MoE), Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1398-6676","authenticated-orcid":false,"given":"Haibin","family":"Cai","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, the Engineering Research Center of Software\/Hardware Co-Design Technology and Application (MoE), Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3174566"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3135752"},{"key":"ref4","first-page":"401","article-title":"Towards scalable distributed training of deep learning on public cloud clusters","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Shi","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3104242"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3517207.3526981"},{"issue":"2","key":"ref7","first-page":"1","article-title":"Parameter server for distributed machine learning","volume-title":"Proc. Big Learn. NIPS Workshop","volume":"6","author":"Li","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987586"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3155284.3018769"},{"article-title":"Horovod: Fast and easy distributed deep learning in tensorflow","year":"2018","author":"Sergeev","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3109097"},{"key":"ref14","first-page":"269","article-title":"Pipemare: Asynchronous pipeline parallel DNN training","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Yang","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118419"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref17","first-page":"418","article-title":"Tictac: Accelerating distributed deep learning with communication scheduling","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Hashemi","year":"2019"},{"key":"ref18","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. MLSys, 2019","volume":"1","author":"Jayarajan"},{"key":"ref19","first-page":"8056","article-title":"Pipe-SGD: A decentralized pipelined SGD framework for distributed deep net training","volume-title":"Proc. NeurIPS","volume":"31","author":"Li","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539086"},{"key":"ref21","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume-title":"Proc. MLSys, 2021","volume":"3","author":"Gebara"},{"key":"ref22","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ML","volume-title":"Proc. MLSys, 2020","volume":"2","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155282"},{"key":"ref24","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. NeurIPS","volume":"30","author":"Alistarh","year":"2017"},{"key":"ref25","first-page":"53","article-title":"3LC: Lightweight and effective traffic compression for distributed machine learning","volume-title":"Proc. MLSys, 2019","volume":"1","author":"Lim"},{"key":"ref26","first-page":"297","article-title":"An efficient statistical-based gradient compression technique for distributed training systems","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Abdelmoniem","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00010"},{"key":"ref28","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. 14th USENIX Symp. Networked Syst. Des. Implementation","author":"Hsieh","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3315847"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2994391"},{"key":"ref31","first-page":"803","article-title":"Slow and stale gradients can win the race: Error-runtime trade-offs in distributed SGD","volume-title":"Proc. AISTATS","author":"Dutta","year":"2018"},{"key":"ref32","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485930"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3117042"},{"key":"ref35","first-page":"365","article-title":"Pufferfish: Communication-efficient models at no extra cost","volume-title":"Proc. MLSys, 2021","volume":"3","author":"Wang"},{"key":"ref36","first-page":"721","article-title":"Slim-DP: A multi-agent system for communication-efficient distributed deep learning","volume-title":"Proc. 17th AAMAS","author":"Sun","year":"2018"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10431415\/10363767.pdf?arnumber=10363767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T11:27:29Z","timestamp":1707823649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10363767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":36,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tc.2023.3343110","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"type":"print","value":"0018-9340"},{"type":"electronic","value":"1557-9956"},{"type":"electronic","value":"2326-3814"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}