Penalized partial least squares for multi-label data

Abstract

Multi-label learning has attracted an increasing attention from many domains, because of its great potential applications. Although many learning methods have been witnessed, two major challenges are still not handled very well. They are the correlations and the high dimensionality of data. In this paper, we exploit the inherent property of the multi-label data and propose an effective sparse multi-label learning algorithm. Specifically, it handles the high-dimensional multi-label data by using a regularized partial least squares discriminant analysis with a l1-norm penalty. Consequently, the proposed method can not only capture the label correlations effectively, but also perform the operation of dimensionality reduction at the same time. The experimental results conducted on eight public data sets show that our method is promising and outperformed the state-of-the-art multi-label classifiers in most cases.