{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:03:15Z","timestamp":1783184595421,"version":"3.54.6"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"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":[],"published-print":{"date-parts":[[2021,7,12]]},"DOI":"10.1109\/isit45174.2021.9518097","type":"proceedings-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T16:52:42Z","timestamp":1630515162000},"page":"1035-1040","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Label Smoothing for Classifier-based Mutual Information Neural Estimation"],"prefix":"10.1109","author":[{"given":"Xu","family":"Wang","sequence":"first","affiliation":[{"name":"City University of Hong Kong,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Al-Bashabsheh","sequence":"additional","affiliation":[{"name":"Big Data and Brain Computing (BDBC) center at Beihang University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung","family":"Chan","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref10","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"On mutual information maximization for representation learning","author":"tschannen","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/18.suppl_2.S231"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.52.2318"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"66138","DOI":"10.1103\/PhysRevE.69.066138","article-title":"Estimating mutual information","volume":"69","author":"kraskov","year":"2004","journal-title":"Phys Rev E"},{"key":"ref16","first-page":"531","article-title":"Mutual information neural estimation","volume":"80","author":"belghazi","year":"2018","journal-title":"Machine Learning Research"},{"key":"ref17","article-title":"On variational lower bounds of mutual information","author":"poole","year":"0","journal-title":"NeurIPS Workshop on Bayesian Deep Learning (NeurIPS BDL)"},{"key":"ref18","first-page":"875","article-title":"Formal limitations on the measurement of mutual information","author":"mcallester","year":"0","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref19","first-page":"307","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","volume":"13","author":"gutmann","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"ref28","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"pereyra","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref4","author":"quinlan","year":"2014","journal-title":"C4 5 Programs for Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref3","author":"yeung","year":"2008","journal-title":"Information Theory and Network Coding"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref29","first-page":"4694","article-title":"When does label smoothing help?","author":"m\u00fcller","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"1558","article-title":"Learning discrete representations via information maximizing self-augmented training","author":"hu","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"ref7","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511921889"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref20","first-page":"2265","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","volume":"26","author":"mnih","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Neural methods for point-wise dependency estimation","author":"tsai","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","volume":"27","author":"levy","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160280102"},{"key":"ref23","first-page":"1083","article-title":"CCMI: Classifier based conditional mutual information estimation","author":"mukherjee","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref26","article-title":"f-gan: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"}],"event":{"name":"2021 IEEE International Symposium on Information Theory (ISIT)","location":"Melbourne, Australia","start":{"date-parts":[[2021,7,12]]},"end":{"date-parts":[[2021,7,20]]}},"container-title":["2021 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9517708\/9517709\/09518097.pdf?arnumber=9518097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:46Z","timestamp":1773347746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9518097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,12]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/isit45174.2021.9518097","relation":{},"subject":[],"published":{"date-parts":[[2021,7,12]]}}}