{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T00:20:08Z","timestamp":1705710008244},"reference-count":17,"publisher":"MIT Press","issue":"2","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Assigning labels to instances is crucial for supervised machine learning. In this letter, we propose a novel annotation method, Q&amp;A labeling, which involves a question generator that asks questions about the labels of the instances to be assigned and an annotator that answers the questions and assigns the corresponding labels to the instances. We derived a generative model of labels assigned according to two Q&amp;A labeling procedures that differ in the way questions are asked and answered. We showed that in both procedures, the derived model is partially consistent with that assumed in previous studies. The main distinction of this study from previous ones lies in the fact that the label generative model was not assumed but, rather, derived based on the definition of a specific annotation method, Q&amp;A labeling. We also derived a loss function to evaluate the classification risk of ordinary supervised machine learning using instances assigned Q&amp;A labels and evaluated the upper bound of the classification error. The results indicate statistical consistency in learning with Q&amp;A labels.<\/jats:p>","DOI":"10.1162\/neco_a_01633","type":"journal-article","created":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T23:18:45Z","timestamp":1702682325000},"page":"312-349","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["Q&amp;A Label Learning"],"prefix":"10.1162","volume":"36","author":[{"given":"Kota","family":"Kawamoto","sequence":"first","affiliation":[{"name":"Waseda University, Tokyo 169-8555, Japan kkwmt0929@ruri.waseda.jp"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Uchida","sequence":"additional","affiliation":[{"name":"Waseda University, Tokyo 169-8555, Japan m.uchida@waseda.jp"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2024,1,18]]},"reference":[{"key":"2024011919410776600_bib1","first-page":"452","article-title":"Classification from pairwise similarity and unlabeled data","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Bao","year":"2018"},{"key":"2024011919410776600_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108447","article-title":"Multi-complementary and unlabeled learning for arbitrary losses and models","volume":"124","author":"Cao","year":"2022","journal-title":"Pattern Recognition"},{"key":"2024011919410776600_bib3","first-page":"1501","article-title":"Learning from partial labels","volume":"12","author":"Cour","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2024011919410776600_bib4","first-page":"3072","article-title":"Learning with multiple complementary labels","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Feng","year":"2020"},{"key":"2024011919410776600_bib5","first-page":"10948","article-title":"Provably consistent partial-label learning","volume-title":"Advances in neural information processing systems","author":"Feng","year":"2020"},{"key":"2024011919410776600_bib6","first-page":"5639","article-title":"Learning from complementary labels","volume-title":"Advances in neural information processing systems","author":"Ishida","year":"2017"},{"key":"2024011919410776600_bib7","first-page":"2971","article-title":"Complementary-label learning for arbitrary losses and models","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Ishida","year":"2019"},{"issue":"2","key":"2024011919410776600_bib8","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1587\/transinf.2021EDP7035","article-title":"Learning from noisy complementary labels with robust loss functions","volume":"E105.D","author":"Ishiguro","year":"2022","journal-title":"IEICE Transactions on Information and Systems"},{"key":"2024011919410776600_bib9","first-page":"161","article-title":"Bridging ordinary-label learning and complementary-label learning","volume-title":"Proceedings of the 12th Asian Conference on Machine Learning","author":"Katsura","year":"2020"},{"issue":"4","key":"2024011919410776600_bib10","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/s42979-021-00681-x","article-title":"A generalization of ordinary-label learning and complementary-label learning","volume":"2","author":"Katsura","year":"2021","journal-title":"SN Computer Science"},{"key":"2024011919410776600_bib11","article-title":"Adam: A method for stochastic optimization","volume-title":"Proceedings of the Third International Conference on Learning Representations","author":"Kingma","year":"2015"},{"key":"2024011919410776600_bib12","first-page":"8734","article-title":"Consistent complementary-label learning via order-preserving losses","volume-title":"Proceedings of the 26th International Conference on Artificial Intelligence and Statistics","author":"Liu","year":"2023"},{"key":"2024011919410776600_bib13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-46379-7_1","article-title":"A vector-contraction inequality for Rademacher complexities","volume-title":"Proceedings of the 27th Algorithmic Learning Theory","author":"Maurer","year":"2016"},{"key":"2024011919410776600_bib14","article-title":"Foundations of machine learning","author":"Mohri","year":"2012"},{"issue":"5","key":"2024011919410776600_bib15","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1162\/neco_a_01373","article-title":"Classification from pairwise similarities\/dissimilarities and unlabeled data via empirical risk minimization","volume":"33","author":"Shimada","year":"2021","journal-title":"Neural Computation"},{"key":"2024011919410776600_bib16","first-page":"11091","article-title":"Leveraged weighted loss for partial label learning","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Wen","year":"2021"},{"key":"2024011919410776600_bib17","first-page":"68","article-title":"Learning with biased complementary labels","volume-title":"Proceedings of the 15th European Conference on Computer Vision","author":"Yu","year":"2018"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/2\/312\/2213733\/neco_a_01633.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/2\/312\/2213733\/neco_a_01633.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T19:41:24Z","timestamp":1705693284000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/36\/2\/312\/118685\/Q-amp-A-Label-Learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,18]]},"references-count":17,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1,18]]},"published-print":{"date-parts":[[2024,1,18]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01633","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,2]]},"published":{"date-parts":[[2024,1,18]]}}}