Max-Coupled Ordinal Classification

Authors

Abstract

Motivated by a breast cancer application, in this work we address a new learning task, in-between classification and semi-supervised classifica- tion. Each example is described using two different feature sets, not nec- essarily both observed for a given example. If a single view is observed, then the class is only due to that feature set; if both views are present the observed class label is the maximum of the two values corresponding to the individual views. We propose new learningmethodologies adapted to this learning para- digm and experimentally compare them with baseline methods from the conventional supervised and unsupervised settings. The experimental re- sults verify the usefulness of the proposed approaches. 1

Conference

17th Portuguese Conference on Pattern Recognition (RECPAD) 2011