{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:06:22Z","timestamp":1774631182181,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Key Laboratory of Scalable Computing and Systems"},{"name":"National Key Laboratory of Ship Structural Safety"},{"name":"Eighth Research Institute of China Aerospace Science and Technology Group Company, Ltd.","award":["USCAST2023-17"],"award-info":[{"award-number":["USCAST2023-17"]}]},{"name":"Eighth Research Institute of China Aerospace Science and Technology Group Company, Ltd.","award":["USCAST2023-21"],"award-info":[{"award-number":["USCAST2023-21"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tc.2024.3485202","type":"journal-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:46:43Z","timestamp":1729705603000},"page":"468-482","source":"Crossref","is-referenced-by-count":4,"title":["FasDL: An Efficient Serverless-Based Training Architecture With Communication Optimization and\u00a0Resource Configuration"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3586-7798","authenticated-orcid":false,"given":"Xinglei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9373-8474","authenticated-orcid":false,"given":"Zinuo","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8538-234X","authenticated-orcid":false,"given":"Hanwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9592-8490","authenticated-orcid":false,"given":"Ruhui","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9754-6496","authenticated-orcid":false,"given":"Rajkumar","family":"Buyya","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cloud programming simplified: A Berkeley view on serverless computing","author":"Jonas","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3508360"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3510611"},{"key":"ref4","article-title":"AWS Lambda"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.76"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2018.053681358"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-013-5050-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.101.2000668"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00027"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737391"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3494884"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3054656"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3570607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3459240"},{"key":"ref15","first-page":"5331","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume":"30","author":"Lian","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.02.006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5 MB model size","author":"Iandola","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511979"},{"key":"ref21","first-page":"303","article-title":"Orion and the three rights: Sizing, bundling, and prewarming for serverless dags","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Mahgoub","year":"2022"},{"key":"ref22","article-title":"AWS Lambda\u2014FAQ","author":"Services","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1085"},{"key":"ref24","article-title":"Parallel coordinate descent for L1-regularized loss minimization","author":"Bradley","year":"2011"},{"key":"ref25","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume":"26","author":"Ho","year":"2013","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref27","article-title":"Amazon Simple Storage Service (S3)"},{"key":"ref28","article-title":"Amazon ElastiCache Serverless"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177734"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337873"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS57198.2023.10188717"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901331"},{"key":"ref34","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00216"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref37","first-page":"307","article-title":"HetPipe: Enabling large DNN training on (whimpy) heterogeneous GPU clusters through integration of pipelined model parallelism and data parallelism","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Park","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3280970"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507717"},{"key":"ref41","first-page":"1489","article-title":"Following the data, not the function: Rethinking function orchestration in serverless computing","volume-title":"Proc. USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Yu","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2022.103405"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2023.3311197"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3513002"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3294406"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3345401"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682915"},{"key":"ref48","first-page":"2826","article-title":"Grapher: A resource-efficient serverless system for GNN serving through graph sharing","volume-title":"Proc. Web Conf.","author":"Hu","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624664"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3330849"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3365134"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3028841"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/10849950\/10732012.pdf?arnumber=10732012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T19:51:22Z","timestamp":1737661882000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10732012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":52,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tc.2024.3485202","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}