Print Email Facebook Twitter To Actively Initialize Active Learning Title To Actively Initialize Active Learning Author Yang, Yazhou (National University of Defense Technology) Loog, M. (TU Delft Pattern Recognition and Bioinformatics; University of Copenhagen) Date 2022 Abstract Though much effort has been spent on designing new active learning algorithms, little attention has been paid to the initialization problem of active learning, i.e., how to find a set of labeled samples which contains at least one instance per category. This work identifies the initialization of active learning as a separate and novel research problem, reviews existing methods that can be adapted to be used for this task and, in addition, proposes a new active initialization criterion: the Nearest Neighbor Criterion. Experiments on 16 benchmark datasets verify that the novel method often finds an initialization set with fewer queried samples than other methods do. Subject active initializationactive learningminimum nearest neighbor distancenearest neighbor criterion To reference this document use: http://resolver.tudelft.nl/uuid:6e229bbf-af89-4ae7-817b-b7989676c94b DOI https://doi.org/10.1016/j.patcog.2022.108836 Embargo date 2023-07-01 ISSN 0031-3203 Source Pattern Recognition, 131 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2022 Yazhou Yang, M. Loog Files PDF 1_s2.0_S003132032200317X_main.pdf 2.64 MB Close viewer /islandora/object/uuid:6e229bbf-af89-4ae7-817b-b7989676c94b/datastream/OBJ/view