{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:35:42Z","timestamp":1787013342392,"version":"build-2736575974"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFB1704003"],"award-info":[{"award-number":["2019YFB1704003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62021002"],"award-info":[{"award-number":["62021002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"R&D Program of Beijing Municipal Education Commission","award":["KM202310028003"],"award-info":[{"award-number":["KM202310028003"]}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["22JCQNJC01520"],"award-info":[{"award-number":["22JCQNJC01520"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua BNRist and Beijing Key Laboratory of Industrial Big Data System and Application"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpds.2023.3266110","type":"journal-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T15:32:02Z","timestamp":1681140722000},"page":"2403-2418","source":"Crossref","is-referenced-by-count":12,"title":["STR: Hybrid Tensor Re-Generation to Break Memory Wall for DNN Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7828-9030","authenticated-orcid":false,"given":"Zan","family":"Zong","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3511-5559","authenticated-orcid":false,"given":"Li","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8230-681X","authenticated-orcid":false,"given":"Leilei","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Management, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0358-3160","authenticated-orcid":false,"given":"Lijie","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7398-2972","authenticated-orcid":false,"given":"Yu","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Dynamic tensor rematerialization","author":"kirisame","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","article-title":"Horovod: Fast and easy distributed deep learning in tensorflow","author":"sergeev","year":"2018"},{"key":"ref12","article-title":"Training deep nets with sublinear memory cost","author":"chen","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref15","first-page":"200","article-title":"Dynamic memory management for GPU-based training of deep neural networks","author":"shriram","year":"2019","journal-title":"Proc IEEE Int Parallel Distrib Process Symp"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref58","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","author":"hashemi","year":"2019","journal-title":"Proc 2nd SysML Conf"},{"key":"ref53","article-title":"Mimose: An input-aware checkpointing planner for efficient training on GPU","author":"liao","year":"2022"},{"key":"ref52","first-page":"4125","article-title":"Memory-efficient backpropagation through time","author":"gruslys","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00101"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref54","article-title":"XEngine: Optimal tensor rematerialization for neural networks in heterogeneous environments","volume":"20","author":"schuler","year":"2022","journal-title":"ACM Trans Archit Code Optim"},{"key":"ref17","article-title":"TFLMS: Large model support in tensorflow by graph rewriting","author":"le","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378530"},{"key":"ref19","first-page":"1161","article-title":"A graph theoretic framework of recomputation algorithms for memory-efficient backpropagation","author":"kusumoto","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532394"},{"key":"ref50","article-title":"Memory optimization for deep networks","author":"shah","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MCHPC49590.2019.00014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508417"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"ref42","first-page":"1","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796792"},{"key":"ref44","first-page":"1","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.icte.2020.04.010","article-title":"The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset","volume":"6","author":"kandel","year":"2020","journal-title":"ICT Express"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547405"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"ref7","first-page":"1","article-title":"Training deeper models by GPU memory optimization on tensorflow","author":"meng","year":"2017","journal-title":"Proc ML Syst Workshop Int Conf Neural Inf Process Syst"},{"key":"ref9","article-title":"Gradient checkpointint","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref3","first-page":"7937","article-title":"Memory-efficient pipeline-parallel DNN training","author":"narayanan","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57675-2_10"},{"key":"ref5","first-page":"497","article-title":"Checkmate: Breaking the memory wall with optimal tensor rematerialization","author":"jain","year":"2020","journal-title":"Proc 3rd Conf Mach Learn Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3063118"},{"key":"ref35","article-title":"The CIFAR-10 dataset","year":"2009"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref36","article-title":"iBUG 300-W face landmark dataset","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF01580724"},{"key":"ref33","article-title":"Tensorflow","year":"2023"},{"key":"ref32","article-title":"Tensorflow profiler: Profile model performance","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3452055"},{"key":"ref1","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"2019","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref39","article-title":"Sentiment analysis of IMDb movie reviews","year":"0"},{"key":"ref38","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","article-title":"Gurobi","year":"2023"},{"key":"ref23","article-title":"Ternausnet: U-net with VGG11 encoder pre-trained on imagenet for image segmentation","author":"iglovikov","year":"2018"},{"key":"ref26","article-title":"NVIDIA NVLink connections","year":"2023"},{"key":"ref25","article-title":"IBM ilog CPLEX optimizer","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015"},{"key":"ref21","article-title":"Deeply-fused nets","author":"wang","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0065773"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0891-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/800057.808695"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10153956\/10098636.pdf?arnumber=10098636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T13:57:41Z","timestamp":1690207061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10098636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":58,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3266110","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}