Show simple item record  

dc.contributor.authorLeathart, Timen_NZ
dc.contributor.authorFrank, Eibeen_NZ
dc.contributor.authorPfahringer, Bernharden_NZ
dc.contributor.authorHolmes, Geoffreyen_NZ
dc.contributor.editorYang, Q.en_NZ
dc.contributor.editorZhou, Z.-H.en_NZ
dc.contributor.editorGong, Z.en_NZ
dc.contributor.editorZhang, M.-L.en_NZ
dc.contributor.editorHuang, S.-J.en_NZ
dc.coverage.spatialMacau, Chinaen_NZ
dc.date.accessioned2019-09-18T23:49:46Z
dc.date.available2019en_NZ
dc.date.available2019-09-18T23:49:46Z
dc.date.issued2019en_NZ
dc.identifier.citationLeathart, T., Frank, E., Pfahringer, B., & Holmes, G. (2019). On calibration of nested dichotomies. In Q. Yang, Z.-H. Zhou, Z. Gong, M.-L. Zhang, & S.-J. Huang (Eds.), Advances in Knowledge Discovery and Data Mining: Proc 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2019), LNCS 11439 (Vol. Part I, pp. 69–80). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-030-16148-4_6en
dc.identifier.isbn978-3-030-16147-7en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/12887
dc.description.abstractNested dichotomies (NDs) are used as a method of transforming a multiclass classification problem into a series of binary problems. A tree structure is induced that recursively splits the set of classes into subsets, and a binary classification model learns to discriminate between the two subsets of classes at each node. In this paper, we demonstrate that these NDs typically exhibit poor probability calibration, even when the binary base models are well-calibrated. We also show that this problem is exacerbated when the binary models are poorly calibrated. We discuss the effectiveness of different calibration strategies and show that accuracy and log-loss can be significantly improved by calibrating both the internal base models and the full ND structure, especially when the number of classes is high.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherSpringeren_NZ
dc.rights© 2019 Springer Nature Switzerland AG. This is the author's accepted version. The final publication is available at Springer via dx.doi.org/10.1007/978-3-030-16148-4_6
dc.subjectcomputer scienceen_NZ
dc.subjectmachine learningen_NZ
dc.titleOn calibration of nested dichotomiesen_NZ
dc.typeConference Contribution
dc.identifier.doi10.1007/978-3-030-16148-4_6en_NZ
dc.relation.isPartOfAdvances in Knowledge Discovery and Data Mining: Proc 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2019), LNCS 11439en_NZ
pubs.begin-page69
pubs.elements-id237117
pubs.end-page80
pubs.finish-date2019-04-17en_NZ
pubs.place-of-publicationCham, Switzerlanden_NZ
pubs.start-date2019-04-14en_NZ
pubs.volumePart Ien_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record