[BibTeX] [RIS]
Reliable Multilabel Classification: Prediction with Partial Abstention
Type of publication: Article
Citation: ln:MlcAbstention
Journal: Proceedings of the AAAI Conference on Artificial Intelligence
Volume: 34
Number: 04
Year: 2020
Month: Apr.
Pages: 5264-5271
URL: https://ojs.aaai.org/index.php/AAAI/article/view/5972
DOI: 10.1609/aaai.v34i04.5972
Abstract: In contrast to conventional (single-label) classification, the setting of multilabel classification (MLC) allows an instance to belong to several classes simultaneously. Thus, instead of selecting a single class label, predictions take the form of a subset of all labels. In this paper, we study an extension of the setting of MLC, in which the learner is allowed to partially abstain from a prediction, that is, to deliver predictions on some but not necessarily all class labels. We propose a formalization of MLC with abstention in terms of a generalized loss minimization problem and present first results for the case of the Hamming loss, rank loss, and F-measure, both theoretical and experimental.
Keywords:
Authors Nguyen, Vu-Linh
Hüllermeier, Eyke
Topics