Feature selection for multi-label classification using multivariate mutual information

Recently, classification tasks that naturally emerge in multi-label domains, such as text categorization, automatic scene annotation, and gene function prediction, have attracted great interest. As in traditional single-label classification, feature selection plays an important role in multi-label classification. However, recent feature selection methods require preprocessing steps that transform the label set into a single label, resulting in subsequent additional problems. In this paper, we propose a feature selection method for multi-label classification that naturally derives from mutual information between selected features and the label set. The proposed method was applied to several multi-label classification problems and compared with conventional methods. The experimental results demonstrate that the proposed method improves the classification performance to a great extent and has proved to be a useful method in selecting features for multi-label classification problems.

► We propose a multivariate mutual information-based feature selection for multi-label classification. ► Label interactions without resorting to problem transformation have been considered. ► The calculation of high-dimensional entropy is decomposed into a cumulative sum of multivariate mutual information.