{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:51:18Z","timestamp":1783788678505,"version":"3.55.0"},"reference-count":52,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3113934","type":"journal-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T20:26:14Z","timestamp":1632169574000},"page":"130834-130844","source":"Crossref","is-referenced-by-count":3,"title":["Learning to Balance Local Losses via Meta-Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2982-0884","authenticated-orcid":false,"given":"Seungdong","family":"Yoa","sequence":"first","affiliation":[{"name":"Department of Computer Science, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0572-6065","authenticated-orcid":false,"given":"Minkyu","family":"Jeon","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1546-8469","authenticated-orcid":false,"given":"Youngjin","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2181-9264","authenticated-orcid":false,"given":"Hyunwoo J.","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref38","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2017","journal-title":"Proc ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-014-0247-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972825.10"},{"key":"ref31","article-title":"Training deeper convolutional networks with deep supervision","author":"wang","year":"2015","journal-title":"arXiv 1505 02496"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_31"},{"key":"ref37","first-page":"3","article-title":"Using meta-learning to initialize Bayesian optimization of hyperparameters","volume":"1201","author":"feurer","year":"2014","journal-title":"Proc Int Conf Meta-Learn Algorithm Selection"},{"key":"ref36","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"franceschi","year":"2018"},{"key":"ref35","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref34","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"li","year":"2017","journal-title":"arXiv 1707 09835"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref27","article-title":"Meta-learning via learned loss","author":"bechtle","year":"2019","journal-title":"arXiv 1906 05374"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00608"},{"key":"ref2","first-page":"7","article-title":"Large-margin softmax loss for convolutional neural networks","volume":"2","author":"liu","year":"2016","journal-title":"Proc ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref20","first-page":"2","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"Proc ICLR"},{"key":"ref22","first-page":"4839","article-title":"Training neural networks with local error signals","author":"n\u00f8kland","year":"2019","journal-title":"Proc ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6229"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00446"},{"key":"ref26","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref25","first-page":"1610","article-title":"Teaching-to-learn and learning-to-teach for multi-label propagation","author":"gong","year":"2016","journal-title":"Proc AAAI"},{"key":"ref50","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref52","first-page":"1085","article-title":"Algorithms for direct 0–1 loss optimization in binary classification","author":"nguyen","year":"2013","journal-title":"Proc ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref11","first-page":"751","article-title":"From baby steps to leapfrog: How,” less is more” in unsupervised dependency parsing","author":"spitkovsky","year":"2010","journal-title":"Proc Hum Lang Technol Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref12","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995523"},{"key":"ref14","first-page":"6467","article-title":"Learning to teach with dynamic loss functions","author":"wu","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref15","article-title":"Learning to teach","author":"fan","year":"2018","journal-title":"Proc ICLR"},{"key":"ref16","article-title":"Learning to teach with deep interactions","author":"fan","year":"2020","journal-title":"arXiv 2007 04649"},{"key":"ref17","first-page":"1917","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","author":"shu","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref18","first-page":"1","article-title":"Learning to optimize","author":"li","year":"2017","journal-title":"Proc ICLR"},{"key":"ref19","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Artif Intell Statist"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref6","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"2149","article-title":"Iterative machine teaching","author":"liu","year":"2017","journal-title":"Proc ICML"},{"key":"ref7","first-page":"5631","article-title":"The teaching dimension of linear learners","volume":"17","author":"liu","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref49","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref9","first-page":"4083","article-title":"Machine teaching: An inverse problem to machine learning and an approach toward optimal education","author":"zhu","year":"2015","journal-title":"Proc AAAI"},{"key":"ref46","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref45","first-page":"1","article-title":"How to train your MAML","author":"antoniou","year":"2019","journal-title":"Proc ICLR"},{"key":"ref48","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref47","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref42","first-page":"3030","article-title":"Learning what and where to transfer","author":"jang","year":"2019","journal-title":"Proc ICML"},{"key":"ref41","first-page":"7693","article-title":"Fast context adaptation via meta-learning","volume":"97","author":"luisa zintgraf","year":"2019","journal-title":"Proc ICML"},{"key":"ref44","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018","journal-title":"arXiv 1803 02999"},{"key":"ref43","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc ICML"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09541196.pdf?arnumber=9541196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:42:38Z","timestamp":1662669758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9541196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3113934","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}