{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T16:11:56Z","timestamp":1760890316898,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA19020400"],"award-info":[{"award-number":["XDA19020400"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3065406","type":"journal-article","created":{"date-parts":[[2021,3,10]],"date-time":"2021-03-10T21:17:48Z","timestamp":1615411068000},"page":"51134-51145","source":"Crossref","is-referenced-by-count":2,"title":["Roulette: A Pruning Framework to Train a Sparse Neural Network From Scratch"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1269-8106","authenticated-orcid":false,"given":"Qiaoling","family":"Zhong","sequence":"first","affiliation":[]},{"given":"Zhibin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"The lottery ticket hypothesis at scale","volume":"abs 1903 1611","author":"frankle","year":"2019","journal-title":"CoRR"},{"key":"ref38","first-page":"760","article-title":"Network pruning via transformable architecture search","author":"dong","year":"2019","journal-title":"Proc Neural Inf Process Syst (NeurIPS)"},{"key":"ref33","first-page":"2082","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/502593"},{"key":"ref31","first-page":"1","article-title":"A survey of sparse matrix-vector multiplication performance on large matrices","volume":"abs 1608 636","author":"grossman","year":"2016","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/1583991.1584053","article-title":"Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks","author":"bulu\u00e7","year":"2009","journal-title":"Proc 21st Annu Symp Parallelism Algorithms Archit"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"ref36","article-title":"AMC: Automl for model compression and acceleration on mobile devices","author":"he","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref27","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 Represent (ICLR)"},{"key":"ref29","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NIPS-W"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"1","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref20","first-page":"1","article-title":"Critical learning periods in deep networks","author":"achille","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","first-page":"471","article-title":"Rigging the lottery: Making all tickets winners","author":"evci","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref21","first-page":"1","article-title":"Drawing early-bird tickets: Toward more efficient training of deep networks","author":"you","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3154815"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2654822.2541967"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3362031"},{"key":"ref25","first-page":"1","article-title":"Resource management in Fog\/Edge computing: A survey on architectures, infrastructure, and algorithms","volume":"52","author":"hong","year":"2019","journal-title":"ACM Comput Surv"},{"key":"ref50","first-page":"103","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3415048.3416114"},{"key":"ref53","first-page":"2232","article-title":"An investigation into neural net optimization via hessian eigenvalue density","volume":"97","author":"ghorbani","year":"2019","journal-title":"Mach Learn Res"},{"key":"ref52","first-page":"1","article-title":"New insights and perspectives on the natural gradient method","volume":"21","author":"martens","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref10","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume":"33","author":"tanaka","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Neural Information Processing Systems"},{"key":"ref40","first-page":"1","article-title":"Deconstructing lottery tickets: Zeros, signs, and the supermask","author":"zhou","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"ref13","first-page":"1","article-title":"Rethinking the value of network pruning","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","first-page":"304","article-title":"Data-driven sparse structure selection for deep neural networks","volume":"abs 1707 1213","author":"huang","year":"2017","journal-title":"CoRR"},{"key":"ref15","first-page":"1","article-title":"Dynamic channel pruning: Feature boosting and suppression","author":"gao","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref17","first-page":"883","article-title":"Discrimination-aware channel pruning for deep neural networks","author":"zhuang","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref18","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume":"70","author":"molchanov","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref19","first-page":"1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref5","first-page":"5753","author":"yang","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref8","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume":"1","author":"han","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref7","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref46","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume":"1","author":"jia","year":"2018","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref48","article-title":"Large batch training of convolutional networks","author":"you","year":"2017","journal-title":"arXiv 1708 03888"},{"key":"ref47","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"shallue","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref42","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","volume":"abs 1704 4861","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref41","first-page":"1","article-title":"The early phase of neural network training","author":"frankle","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref44","first-page":"1967","article-title":"Pelee: A real-time object detection system on mobile devices","author":"wang","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09374983.pdf?arnumber=9374983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T21:42:46Z","timestamp":1698010966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9374983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3065406","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}