{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T08:40:17Z","timestamp":1768984817962,"version":"3.49.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER CMMI-1750531"],"award-info":[{"award-number":["CAREER CMMI-1750531"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-1609916"],"award-info":[{"award-number":["ECCS-1609916"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1919117"],"award-info":[{"award-number":["CCF-1919117"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1909172"],"award-info":[{"award-number":["CNS-1909172"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1704662"],"award-info":[{"award-number":["CNS-1704662"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/tnnls.2020.3045153","type":"journal-article","created":{"date-parts":[[2021,2,16]],"date-time":"2021-02-16T14:58:14Z","timestamp":1613487494000},"page":"2259-2273","source":"Crossref","is-referenced-by-count":35,"title":["StructADMM: Achieving Ultrahigh Efficiency in Structured Pruning for DNNs"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2475-6414","authenticated-orcid":false,"given":"Tianyun","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"given":"Shaokai","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"given":"Xiaoyu","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3753-7648","authenticated-orcid":false,"given":"Xiaolong","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}]},{"given":"Kaiqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"given":"Zhengang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4418-0114","authenticated-orcid":false,"given":"Jian","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-6991","authenticated-orcid":false,"given":"Sijia","family":"Liu","sequence":"additional","affiliation":[{"name":"IBM Cambridge Research Center, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6210-8883","authenticated-orcid":false,"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-2309","authenticated-orcid":false,"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4643-0535","authenticated-orcid":false,"given":"Makan","family":"Fardad","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3024-7990","authenticated-orcid":false,"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2015.7326945"},{"key":"ref7","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":"ref8","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2914438"},{"key":"ref10","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref12","first-page":"2148","article-title":"Predicting parameters in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denil"},{"key":"ref13","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2014","author":"Denton"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.78"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.327"},{"key":"ref16","first-page":"3088","article-title":"Structured transforms for small-footprint deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sindhwani"},{"key":"ref17","first-page":"4082","article-title":"Theoretical properties for neural networks with weight matrices of low displacement rank","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Zhao"},{"key":"ref18","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref19","first-page":"4860","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref20","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Molchanov"},{"key":"ref21","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"arXiv:1803.03635","author":"Frankle","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref23","article-title":"Learning sparse neural networks through L\u2080 regularization","volume-title":"arXiv:1712.01312","author":"Louizos","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/9781601984616"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1034-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"ref29","article-title":"Exploring the regularity of sparse structure in convolutional neural networks","volume-title":"arXiv:1705.08922","author":"Mao","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref31","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","volume-title":"arXiv:1702.03044","author":"Zhou","year":"2017"},{"key":"ref32","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref35","first-page":"4107","article-title":"Binarized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304076"},{"key":"ref37","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Courbariaux"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref40","article-title":"Distilling the knowledge in a neural network","volume-title":"arXiv:1503.02531","author":"Hinton","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref42","first-page":"4027","article-title":"SCAN: A scalable neural networks framework towards compact and efficient models","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref43","first-page":"395","article-title":"CirCNN: Accelerating and compressing deep neural networks using block-circulant weight matrices","volume-title":"Proc. 50th Annu. IEEE\/ACM Int. Symp. Microarchitecture","author":"Ding"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref45","article-title":"Pruning filters for efficient ConvNets","volume-title":"arXiv:1608.08710","author":"Li","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref47","first-page":"875","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref48","article-title":"Deephoyer: Learning sparser neural network with differentiable scale-invariant sparsity measures","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2017.1316016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11713"},{"issue":"1","key":"ref53","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML","volume":"30","author":"Maas"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2013.6736834"},{"key":"ref57","article-title":"CuDNN: Efficient primitives for deep learning","volume-title":"arXiv:1410.0759","author":"Chetlur","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/140990309"},{"key":"ref59","first-page":"288","article-title":"Zeroth-order online alternating direction method of multipliers: Convergence analysis and applications","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"2018","author":"Liu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref62","article-title":"2PFPCE: Two-phase filter pruning based on conditional entropy","volume-title":"arXiv:1809.02220","author":"Min","year":"2018"},{"key":"ref63","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume-title":"arXiv:1212.0402","author":"Soomro","year":"2012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1017\/9781108924238.008"},{"key":"ref68","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. OSDI","author":"Chen"},{"key":"ref69","article-title":"Rethinking the value of network pruning","volume-title":"arXiv:1810.05270","author":"Liu","year":"2018"},{"key":"ref70","article-title":"Learning spatiotemporal features with 3D convolutional networks","volume-title":"arXiv:1412.0767","author":"Tran","year":"2014"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9766240\/9354506-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9766240\/09354506.pdf?arnumber=9354506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:53:34Z","timestamp":1704840814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9354506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":70,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3045153","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5]]}}}