{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:32:00Z","timestamp":1772119920860,"version":"3.50.1"},"reference-count":38,"publisher":"MIT Press - Journals","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2020,3]]},"abstract":"<jats:p>Learning from triplet comparison data has been extensively studied in the context of metric learning, where we want to learn a distance metric between two instances, and ordinal embedding, where we want to learn an embedding in a Euclidean space of the given instances that preserve the comparison order as much as possible. Unlike fully labeled data, triplet comparison data can be collected in a more accurate and human-friendly way. Although learning from triplet comparison data has been considered in many applications, an important fundamental question of whether we can learn a classifier only from triplet comparison data without all the labels has remained unanswered. In this letter, we give a positive answer to this important question by proposing an unbiased estimator for the classification risk under the empirical risk minimization framework. Since the proposed method is based on the empirical risk minimization framework, it inherently has the advantage that any surrogate loss function and any model, including neural networks, can be easily applied. Furthermore, we theoretically establish an estimation error bound for the proposed empirical risk minimizer. Finally, we provide experimental results to show that our method empirically works well and outperforms various baseline methods.<\/jats:p>","DOI":"10.1162\/neco_a_01262","type":"journal-article","created":{"date-parts":[[2020,1,17]],"date-time":"2020-01-17T22:33:43Z","timestamp":1579300423000},"page":"659-681","source":"Crossref","is-referenced-by-count":21,"title":["Classification from Triplet Comparison Data"],"prefix":"10.1162","volume":"32","author":[{"given":"Zhenghang","family":"Cui","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo 113-0033, Japan, and RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan"}]},{"given":"Nontawat","family":"Charoenphakdee","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo 113-0033, Japan, and RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan"}]},{"given":"Issei","family":"Sato","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo 113-0033, Japan, and RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan"}]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan and The University of Tokyo, Tokyo 113-0033, Japan"}]}],"member":"281","reference":[{"key":"B1","first-page":"11","author":"Agarwal S.","year":"2007","journal-title":"Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics"},{"key":"B2","first-page":"282","author":"Anderton J.","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"B3","unstructured":"Asuncion, A. & Newman, D. (2007). UCI machine learning repository. Irvine, CA: University of California, Irvine. http:\/\/archive.ics.uci.edu\/ml"},{"key":"B4","first-page":"452","author":"Bao H.","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"B5","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1145\/1273496.1273523","author":"Davis J. V.","year":"2007","journal-title":"Proceedings of the 24th International Conference on Machine Learning"},{"key":"B6","first-page":"703","volume-title":"Advances in neural information processing systems","volume":"27","author":"du Plessis M. C.","year":"2014"},{"key":"B7","volume-title":"Preference learning","author":"F\u00fcrnkranz J.","year":"2010"},{"key":"B8","first-page":"1871","author":"Haghiri S.","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"B9","first-page":"851","author":"Haghiri S.","year":"2017","journal-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics"},{"key":"B10","author":"Heim E.","year":"2016","journal-title":"Efficiently and effectively learning models of similarity from human feedback"},{"key":"B11","author":"Kingma D. P.","year":"2014","journal-title":"Proceedings of the 3rd International Conference on Learning Representations"},{"key":"B12","author":"Kleindessner M.","year":"2017","journal-title":"Machine learning in a setting of ordinal distance information"},{"key":"B13","first-page":"6807","volume-title":"Advances in neural information processing systems, 30","author":"Kleindessner M.","year":"2017"},{"issue":"1","key":"B14","first-page":"1889","volume":"18","author":"Kleindessner M.","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"B15","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky A.","year":"2009"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"B17","first-page":"516","volume-title":"Proceedings of the 2004 IEEE International Conference on Mobile Ad-hoc and Sensor Systems","author":"Liu C.","year":"2004"},{"key":"B18","author":"Lu N.","year":"2019","journal-title":"Proceedings of the International Conference on Learning Representations 2019"},{"key":"B19","first-page":"281","volume-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability","author":"Macqueen J.","year":"1967"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975673.52"},{"key":"B21","first-page":"394","volume":"26","author":"Moore E. H.","year":"1920","journal-title":"Bull. Am. Math. Soc."},{"key":"B22","first-page":"807","author":"Nair V.","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning"},{"key":"B23","first-page":"2913","volume-title":"Advances in neural information processing systems","volume":"26","author":"Narasimhan H.","year":"2013"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00614"},{"key":"B25","first-page":"1199","author":"Niu G.","year":"2016","journal-title":"NeurIPS"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1017\/S0305004100030401"},{"key":"B27","first-page":"1844","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","author":"Perrot M.","year":"2018"},{"key":"B28","first-page":"815","author":"Schroff F.","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B29","first-page":"41","volume-title":"Advances in neural information processing systems","volume":"17","author":"Schultz M.","year":"2004"},{"key":"B30","author":"Shimada T.","year":"2019","journal-title":"Classification from pairwise similarities\/dissimilarities and unlabeled data via empirical risk minimization"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.112.4.881"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21551-3_31"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2012.6349720"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"B35","author":"Xiao H.","year":"2017","journal-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms"},{"key":"B36","first-page":"2:1","author":"Xiao L.","year":"2006","journal-title":"STRESS"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_5"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:43:31Z","timestamp":1615585411000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/32\/3\/659-681\/95579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["10.1162\/neco_a_01262"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01262","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}