{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:40:45Z","timestamp":1772822445022,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"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":["CNS-1908658"],"award-info":[{"award-number":["CNS-1908658"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Texas State University Research Enhancement Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021,7,1]]},"DOI":"10.1109\/tpds.2020.3047003","type":"journal-article","created":{"date-parts":[[2020,12,23]],"date-time":"2020-12-23T20:24:10Z","timestamp":1608755050000},"page":"1765-1776","source":"Crossref","is-referenced-by-count":40,"title":["Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression"],"prefix":"10.1109","volume":"32","author":[{"given":"Cody","family":"Blakeney","sequence":"first","affiliation":[]},{"given":"Xiaomin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2693-7419","authenticated-orcid":false,"given":"Ziliang","family":"Zong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CSCloud-EdgeCom49738.2020.00051"},{"key":"ref38","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref33","first-page":"iii-1337","article-title":"Deep learning with COTS HPC systems","author":"coates","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref32","article-title":"Revisiting small batch training for deep neural networks","author":"masters","year":"2018"},{"key":"ref31","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref37","article-title":"Stagewise knowledge distillation","author":"kulkarni","year":"2019"},{"key":"ref36","article-title":"An embarrassingly simple approach for knowledge distillation","author":"gao","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/19M1247620"},{"key":"ref34","article-title":"Why M heads are better than one: Training a diverse ensemble of deep networks","author":"lee","year":"2015"},{"key":"ref10","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"denton","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref40","article-title":"Bin packing Python library","author":"maie","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref12","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"lebedev","year":"2014"},{"key":"ref13","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref14","article-title":"Structured pruning of deep convolutional neural networks","volume":"13","author":"sung","year":"2017","journal-title":"ACM J Emerg Technol Comput Syst"},{"key":"ref15","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/384"},{"key":"ref28","article-title":"Model compression via distillation and quantization","author":"polino","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201329"},{"key":"ref27","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"mishra","year":"2017"},{"key":"ref3","article-title":"Faster gaze prediction with dense networks and fisher pruning","author":"theis","year":"2018"},{"key":"ref6","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014"},{"key":"ref29","article-title":"N2N learning: Network to network compression via policy gradient reinforcement learning","author":"ashok","year":"2017"},{"key":"ref5","article-title":"High quality monocular depth estimation via transfer learning","author":"alhashim","year":"2018"},{"key":"ref8","article-title":"Improving the speed of neural networks on CPUs","author":"vanhoucke","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref2","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref9","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173791"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref20","article-title":"AI and compute","author":"hernandez","year":"2018"},{"key":"ref45","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref22","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IGCC.2015.7393699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref42","year":"0"},{"key":"ref24","article-title":"Exploring the regularity of sparse structure in convolutional neural networks","author":"mao","year":"2017"},{"key":"ref41","article-title":"Work stealing","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062259"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9357351\/9305986-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9357351\/09305986.pdf?arnumber=9305986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:31Z","timestamp":1652194231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9305986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":47,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2020.3047003","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":[[2021,7,1]]}}}