{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:48:20Z","timestamp":1764175700235,"version":"3.37.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0110104"],"award-info":[{"award-number":["2021ZD0110104"]}]},{"name":"NSFC for Distinguished Young Scholar","award":["62225206"],"award-info":[{"award-number":["62225206"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2027","62302251"],"award-info":[{"award-number":["U23B2027","62302251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20230193"],"award-info":[{"award-number":["BX20230193"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tpds.2024.3462092","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T18:54:19Z","timestamp":1726599259000},"page":"2208-2223","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Inference for Pruned CNN Models on Mobile Devices With Holistic Sparsity Alignment"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2358-3395","authenticated-orcid":false,"given":"Yuyang","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8654-0192","authenticated-orcid":false,"given":"Runxin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7119-8673","authenticated-orcid":false,"given":"Saiqin","family":"Long","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2024","key":"ref1","article-title":"Arm Compute Library"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00154"},{"key":"ref4","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Chen"},{"key":"ref5","first-page":"646","article-title":"SecureNets: Secure inference of deep neural networks on an untrusted cloud","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.04.031"},{"article-title":"Rethinking bottleneck structure for efficient mobile network design","year":"2020","author":"Daquan","key":"ref8"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0898-1221(76)90003-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP49362.2020.00039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414655"},{"year":"2024","key":"ref14","article-title":"TensorFlow Lite"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref17","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","year":"2021","author":"Hoefler","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303949"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650063"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3247808"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref28"},{"key":"ref29","first-page":"84","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"article-title":"On-device neural net inference with mobile GPUs","year":"2019","author":"Lee","key":"ref31"},{"article-title":"Pruning filters for efficient convnets","year":"2016","author":"Li","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00042"},{"article-title":"Micronet: Towards image recognition with extremely low flops","year":"2020","author":"Li","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3381214"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210337"},{"article-title":"Efficient sparse-winograd convolutional neural networks","year":"2018","author":"Liu","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"article-title":"An introduction to convolutional neural networks","year":"2015","author":"O\u2019Shea","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304076"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref45"},{"key":"ref46","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835939"},{"article-title":"Antnets: Mobile convolutional neural networks for resource efficient image classification","year":"2019","author":"Xiong","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313591"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4244"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3093234"},{"key":"ref52","first-page":"739","article-title":"Optimizing tensor programs with derivation-based transformations","volume-title":"Proc. 17th USENIX Symp. Operating Syst. Des. Implementation","author":"Zheng"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","year":"2017","author":"Zhu","key":"ref54"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10670174\/10682058.pdf?arnumber=10682058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:26:07Z","timestamp":1727976367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":54,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3462092","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}