PU Matrix Completion Based Multi-label Classification with Missing Labels

Abstract

Multi-label classification has attracted significant interests in various domains. However, only few positive labels are labeled. Treating unknown labels as negative labels brings the one-side noise, which causes the severe performance degradation. Motivated by this, we present the positive and unlabeled (PU) matrix completion based Multi-Label Classification with Missing Labels called PUMCML, that focus on finding all positive labels and construct a classifier based on completion matrix under instance and label dependencies. More specifically, an asymmetrical PU learning loss function is firstly used to solve the one-side noise from missing labels. Secondly, an instance dependencies assumption is proposed that similar instances in multi-label data will share similar labels. Furthermore, considering the label dependencies, the completion matrix consisting of the predicted labels and origin labels is constrained by a nuclear norm. Finally, the proposed algorithm is optimization problem which is convex but not smooth, so Alternating Direction Multiplier Method is design for handling the optimization problem by dividing the problem into multiple subproblems. Experimental results on four benchmarks demonstrate our method achieves a huge improvement in performance and robustness to missing labels compared to other advanced algorithms.