Multi-label classification using stacked spectral kernel discriminant analysis

Abstract

Multi-label classification is a challenging research problem due to the fact that each example may belong to a varying number of classes. This problem can be further aggravated by high dimensionality and complex correlation among labels. In this paper, a discriminant approach to multi-label classification is proposed using the concept of stacking and spectral regression based kernel discriminant analysis (SSRKDA). For effective stacked generalisation, a novel fast implementation of the leave-one-out cross-validation for SSRKDA is also presented in this paper. The proposed system is validated on several multi-label databases. The results indicate a significant boost in performance when SSRKDA is compared to other multi-label classification techniques.