{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:14:30Z","timestamp":1775913270388,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tc.2020.2970917","type":"journal-article","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T20:48:25Z","timestamp":1580503705000},"page":"1-1","source":"Crossref","is-referenced-by-count":9,"title":["Accelerating Deep Learning Systems via Critical Set Identification and Model Compression"],"prefix":"10.1109","author":[{"given":"Rui","family":"Han","sequence":"first","affiliation":[]},{"given":"Chi Harold","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shilin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shilin","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Xue","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/2336664.2336675"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2742482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486028"},{"key":"ref32","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $<$<0.5mb model size","author":"iandola","year":"2016"},{"key":"ref31","first-page":"1","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"hubara","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref30","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref37","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","article-title":"A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","first-page":"2525","article-title":"Not all samples are created equal: Deep learning with importance sampling","author":"katharopoulos","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"157","article-title":"Deep learning for content-based image retrieval: A comprehensive study","author":"ji","year":"2014","journal-title":"Proc 22nd ACM Int Conf Multimedia"},{"key":"ref60","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391241"},{"key":"ref27","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","author":"hanson","year":"1989","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/253262.253291"},{"key":"ref2","year":"2012"},{"key":"ref1","year":"2009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","article-title":"Approximate query processing: Taming the TeraBytes","author":"garofalakis","year":"2001","journal-title":"Proc 27th Int Conf Very Large Data Bases"},{"key":"ref21","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2923197"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2017.2730882"},{"key":"ref26","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":"ref25","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1145\/2810103.2813687","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"Proc 22nd ACM SIGSAC Conf Comput Commun Secur"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267810"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2045657"},{"key":"ref56","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2018.8644593"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-7533-0_95"},{"key":"ref53","first-page":"3","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume":"56","author":"song","year":"2015","journal-title":"FIBER"},{"key":"ref52","first-page":"8590","article-title":"CoCoA: A general framework for communication-efficient distributed optimization","volume":"18","author":"smith","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref11","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","volume":"14","author":"chilimbi","year":"2014","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"},{"key":"ref40","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1837274.1837411"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2013.6810241"},{"key":"ref14","first-page":"21","article-title":"MapReduce online","author":"condie","year":"2010","journal-title":"Proc 7th USENIX Conf Netw Syst Des Implementation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362707"},{"key":"ref16","first-page":"1","article-title":"Petuum: A framework for iterative-convergent distributed ML","author":"dai","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","article-title":"GossipGraD: Scalable deep learning using gossip communication based asynchronous gradient descent","author":"daily","year":"2018"},{"key":"ref18","first-page":"2674","article-title":"Taming the wild: A unified analysis of hogwild-style algorithms","author":"de sa","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref4","year":"2018"},{"key":"ref3","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465355"},{"key":"ref5","year":"2019"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1007\/978-3-642-35289-8_26","article-title":"Practical recommendations for gradient-based training of deep architectures","author":"bengio","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref7","first-page":"1707","article-title":"Communication-efficient stochastic gradient descent, with applications to neural networks","author":"alistarh","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767738"},{"key":"ref9","first-page":"1454","article-title":"Importance sampling tree for large-scale empirical expectation","author":"canevet","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref46","article-title":"Online batch selection for faster training of neural networks","author":"loshchilov","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","article-title":"AutoSlim: An automatic DNN structured pruning framework for ultra-high compression rates","author":"liu","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/72.572104"},{"key":"ref47","first-page":"525","article-title":"XNOR-Net: ImageNet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989426"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2908175"},{"key":"ref43","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","volume":"14","author":"li","year":"2014","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/4358213\/08977355.pdf?arnumber=8977355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:16:12Z","timestamp":1651068972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8977355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tc.2020.2970917","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":[[2020]]}}}