{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:11:15Z","timestamp":1770225075441,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022LZH010"],"award-info":[{"award-number":["ZR2022LZH010"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["2208317"],"award-info":[{"award-number":["2208317"]}]},{"name":"NSF","award":["2204657"],"award-info":[{"award-number":["2204657"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tc.2023.3315847","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T17:43:32Z","timestamp":1695231812000},"page":"30-43","source":"Crossref","is-referenced-by-count":6,"title":["ASHL: An Adaptive Multi-Stage Distributed Deep Learning Training Scheme for Heterogeneous Environments"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9526-6634","authenticated-orcid":false,"given":"Zhaoyan","family":"Shen","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8751-6070","authenticated-orcid":false,"given":"Qingxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6630-7791","authenticated-orcid":false,"given":"Tianren","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0118-8135","authenticated-orcid":false,"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7769-4771","authenticated-orcid":false,"given":"Zhiping","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6835-5981","authenticated-orcid":false,"given":"Dongxiao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8782-2730","authenticated-orcid":false,"given":"Zhiyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Quan Cheng Laboratory, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5815-9706","authenticated-orcid":false,"given":"Bingzhe","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Texas at Dallas, Richardson, TX, USA"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","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":"ref2","first-page":"1","article-title":"Optimizing network performance in distributed machine learning","volume-title":"Proc. 7th USENIX Workshop Hot Topics Cloud Comput. (HotCloud)","author":"Mai","year":"2015"},{"key":"ref3","first-page":"629","article-title":"Gaia: Geo-Distributed machine learning approaching LAN speeds","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Hsieh","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452773"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref8","first-page":"265","article-title":"TensorFlow: A system for Large-Scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Abadi","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS47876.2019.00068"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488810"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6207"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2020.11.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295285"},{"key":"ref14","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Huang","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref16","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. (ATC)","author":"Park","year":"2020"},{"key":"ref17","article-title":"Measuring the effects of data parallelism on neural network training","author":"Shallue","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1085"},{"key":"ref20","article-title":"Revisiting distributed synchronous SGD","author":"Chen","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref22","first-page":"1232","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Dean","year":"2012"},{"key":"ref23","first-page":"693","article-title":"Hogwild!: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Recht","year":"2011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref25","article-title":"Slow learners are fast","author":"Langford","year":"2009"},{"key":"ref26","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Ho","year":"2013"},{"key":"ref27","first-page":"37","article-title":"Exploiting bounded staleness to speed up big data analytics","volume-title":"Proc. USENIX Annu. Tech. Conf. (ATC)","author":"Cui","year":"2014"},{"key":"ref28","first-page":"2530","article-title":"A linear speedup analysis of distributed deep learning with sparse and quantized communication","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jiang","year":"2018"},{"key":"ref29","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yu","year":"2019"},{"key":"ref30","first-page":"213:1","article-title":"Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms","volume-title":"J. Mach. Learn. Res.","volume":"22","author":"Wang","year":"2021"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"ref37","article-title":"Deep Gradient Compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2017"},{"key":"ref38","first-page":"14668","article-title":"Qsparse-local-SGD: Distributed SGD with quantization, sparsification and local computations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Basu","year":"2019"},{"key":"ref39","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. PMLR Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Reisizadeh","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3062398"},{"key":"ref41","first-page":"1","article-title":"Don\u2019t use large mini-batches, use local SGD","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lin","year":"2019"},{"key":"ref42","first-page":"463","article-title":"A unified architecture for accelerating distributed","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Jiang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421307"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.05.032"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10372122\/10256683.pdf?arnumber=10256683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T03:57:48Z","timestamp":1705031868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10256683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tc.2023.3315847","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":[[2024,1]]}}}