PARIS: Partial instance and training set selection. A new scalable approach to multi-label classification

Abstract

Multi-label classification has recently attracted research interest as a data mining task. Many current applications in data mining address problems that have instances belonging to more than one class. This requires the development of new efficient methods. Instance selection has been used in multi-label learning to improve the execution time and classification performance of many learning methods. Following the single-label approach, instance selection has been applied by selecting or unselecting the same instances for all labels. In this paper, we present a different and novel approach. An instance might be useful for some labels and harmful for others; therefore, our algorithm allows each instance to be discarded, selected, or only partially selected for use in the classification of certain labels. An extensive comparison using 45 datasets shows the usefulness of our approach in improving the current instance selection methods for multi-label problems, as well as the ability of our algorithm to compete with other more complex multi-label classification methods.