{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:22:56Z","timestamp":1740165776942,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101402"],"award-info":[{"award-number":["2018AAA0101402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811463"],"award-info":[{"award-number":["U1811463"]}],"id":[{"id":"10.13039\/501100001809","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":[[2022,11]]},"DOI":"10.1109\/tnnls.2021.3079112","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T19:37:15Z","timestamp":1621885035000},"page":"6360-6372","source":"Crossref","is-referenced-by-count":1,"title":["Drill the Cork of Information Bottleneck by Inputting the Most Important Data"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7181-2159","authenticated-orcid":false,"given":"Xinyu","family":"Peng","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9185-3989","authenticated-orcid":false,"given":"Fei-Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9428-1960","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref4","article-title":"WaveNet: A generative model for raw audio","author":"van den Oord","year":"2016","journal-title":"arXiv:1609.03499"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v13i1.12929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref11","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref12","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref13","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","author":"You","year":"2019","journal-title":"arXiv:1904.00962"},{"key":"ref14","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv:physics\/0004057"},{"key":"ref15","article-title":"Flow of information in feed-forward deep neural networks","author":"Khadivi","year":"2016","journal-title":"arXiv:1603.06220"},{"key":"ref16","article-title":"Emergence of invariance and disentanglement in deep representations","author":"Achille","year":"2017","journal-title":"arXiv:1706.01350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"ref18","article-title":"Deep variational information bottleneck","author":"Alemi","year":"2016","journal-title":"arXiv:1612.00410"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2784440"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref21","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/e21121181"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10445-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/e21050456"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref27","first-page":"1","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Johnson"},{"key":"ref28","first-page":"2663","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"4","author":"Roux"},{"issue":"7","key":"ref29","first-page":"257","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.746"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2010.04.006"},{"key":"ref34","article-title":"Understanding intermediate layers using linear classifier probes","author":"Alain","year":"2016","journal-title":"arXiv:1610.01644"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3a74"},{"volume-title":"Sampling: Design Analysis","year":"2009","author":"Lohr","key":"ref37"},{"key":"ref38","article-title":"Big batch SGD: Automated inference using adaptive batch sizes","author":"De","year":"2016","journal-title":"arXiv:1610.05792"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/110830629"},{"key":"ref40","article-title":"Variance reduction in sgd by distributed importance sampling","author":"Alain","year":"2015","journal-title":"arXiv:1511.06481"},{"key":"ref41","article-title":"Accelerating minibatch stochastic gradient descent using stratified sampling","author":"Zhao","year":"2014","journal-title":"arXiv:1405.3080"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511569920.005"},{"key":"ref43","article-title":"Convergence diagnostics for stochastic gradient descent with constant step size","author":"Chee","year":"2017","journal-title":"arXiv:1710.06382"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/e19070361"},{"journal-title":"UCI Machine Learning Repository","year":"2017","author":"Dua","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref48"},{"key":"ref49","article-title":"Decoupling representation and classifier for long-tailed recognition","author":"Kang","year":"2019","journal-title":"arXiv:1910.09217"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref52","first-page":"1567","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9931397\/09439803.pdf?arnumber=9439803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:14:23Z","timestamp":1704842063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9439803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3079112","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}