{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:49:44Z","timestamp":1757314184276,"version":"3.37.3"},"reference-count":82,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533659","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["Learn and Visually Explain Deep Fair Models: an Application to Face Recognition"],"prefix":"10.1109","author":[{"given":"Danilo","family":"Franco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Oneto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolo","family":"Navarin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Anguita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"journal-title":"Reproducing Kernel Hilbert Spaces in Probability and Statistics","year":"2011","author":"berlinet","key":"ref71"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-015-5540-x"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20828-2"},{"journal-title":"Optimal Transport Old and New","year":"2008","author":"villani","key":"ref77"},{"key":"ref74","article-title":"On the transfer of masses (in russian)","author":"kantorovich","year":"1942","journal-title":"Doklady Akademii Nauk USSR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00269"},{"key":"ref75","article-title":"Interpolating between optimal transport and mmd using sinkhorn divergences","author":"feydy","year":"0","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref38","article-title":"Adversarially learned representations for information obfuscation and inference","author":"bertran","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/e19020047"},{"key":"ref79","article-title":"Fairface: Face attribute dataset for balanced race, gender, and age","author":"k\u00e4rkk\u00e4inen","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"Learning adversarially fair and transferable representations","author":"madras","year":"0","journal-title":"International Conference on Machine Learning 2018"},{"key":"ref32","article-title":"Controllable invariance through adversarial feature learning","author":"xie","year":"0","journal-title":"Advances in Neural Information Processing Systems 2017"},{"key":"ref31","article-title":"Disentangling factors of variation in deep representation using adversarial training","author":"mathieu","year":"0","journal-title":"Neural Inform Process Syst 2016"},{"key":"ref30","article-title":"Censoring representations with an adversary","author":"edwards","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012412"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00541"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00922"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622525"},{"key":"ref60","article-title":"Imagenet classification with deep convolutional neural networks","author":"a","year":"0","journal-title":"Advances in Neural Information Processing Systems 2012"},{"key":"ref62","article-title":"Ablation-cam: Visual explanations for deep convolutional network via gradient-free localization","author":"desai","year":"0","journal-title":"IEEE Winter Conference on Applications of Computer Vision"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00886"},{"key":"ref28","article-title":"Invariant representations without adversarial training","author":"moyer","year":"0","journal-title":"Advances in Neural Information Processing Systems 2018"},{"key":"ref64","article-title":"A generic visualization approach for convolutional neural networks","author":"taha","year":"0","journal-title":"IEEE European Conference on Computer Vision"},{"key":"ref27","article-title":"Optimized data pre-processing for discrimination prevention","author":"calmon","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref65","article-title":"Toward interpretable machine learning: Transparent deep neural networks and beyond","author":"samek","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref66","article-title":"Explaining convolutional neural networks through attribution-based input sampling and blockwise feature aggregation","author":"sattarzadeh","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Hierarchical vampprior variational fair auto-encoder","author":"botros","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"journal-title":"The Theory of Approximate Methods and Their Application to the Numerical Solution of Singular Integral Equations","year":"1976","author":"ivanov","key":"ref69"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2019.06.012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref22","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Efficient $L$1 regularized logistic regression","volume":"6","author":"lee","year":"2006","journal-title":"AAAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00121"},{"key":"ref26","article-title":"The variational fair autoencoder","author":"louizos","year":"0","journal-title":"International Conference in Learning Representations 2016"},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Int Conf Learning Representations 2014"},{"key":"ref50","article-title":"Learning representations for counterfactual inference","author":"johansson","year":"0","journal-title":"International Conference on Machine Learning Jun 2016"},{"key":"ref51","article-title":"Equality of opportunity in supervised learning","author":"hardt","year":"0","journal-title":"Neural Inform Process Syst 2016"},{"key":"ref59","article-title":"Adadelta: an adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref57","article-title":"The elements of end-to-end deep face recognition: A survey of recent advances","author":"du","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102805"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00067"},{"key":"ref54","article-title":"Deep face recognition: A survey","author":"wang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref53","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"International Conference on Learning Representations ICLR 2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24359-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.06.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00806"},{"key":"ref12","article-title":"Learning fair representations","author":"zemel","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314243"},{"key":"ref14","article-title":"Exploiting mmd and sinkhorn divergences for fair and transferable representation learning","author":"oneto","year":"0","journal-title":"Advances in Neural Information Processing Systems 2020"},{"key":"ref15","article-title":"Empirical risk minimization under fairness constraints","author":"donini","year":"0","journal-title":"Advances in Neural Information Processing Systems 2018"},{"journal-title":"Matrix Computations","year":"1983","author":"van loan","key":"ref82"},{"key":"ref16","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"cuturi","year":"0","journal-title":"Advances in Neural Information Processing Systems 2013"},{"key":"ref81","article-title":"Diversity in faces","author":"merler","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"A kernel method for the two-sample-problem","author":"gretton","year":"0","journal-title":"Advances in Neural Information Processing Systems 2006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.83"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3194770.3194776"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref4","first-page":"671","article-title":"Big data's disparate impact","volume":"104","author":"barocas","year":"2016","journal-title":"California Law Review"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11222"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2018.01.039"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3317964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2017.0387"},{"key":"ref46","article-title":"Decoupled classifiers for group-fair and efficient machine learning","author":"dwork","year":"0","journal-title":"Conference on Fairness Accountability and Transparency"},{"key":"ref45","article-title":"Learning controllable fair representations","author":"song","year":"0","journal-title":"International Conference on Artificial Intelligence and Statistics 2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43883-8_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314255"},{"key":"ref42","article-title":"Conditional learning of fair representations","author":"zhao","year":"0","journal-title":"International Conference on Learning Representations 2020"},{"key":"ref41","article-title":"Fair representation for safe artificial intelligence via adversarial learning of unbiased information bottleneck","author":"kim","year":"0","journal-title":"Workshop on Artificial Intelligence Safety 2020"},{"key":"ref44","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Advances in Neural Information Processing Systems 2014"},{"key":"ref43","article-title":"Sensitivenets: Learning agnostic representations with application to face images","author":"morales","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533659.pdf?arnumber=9533659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:51Z","timestamp":1652197551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533659\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533659","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}