Complementary label learning with multi-view data and a semi-supervised labeling mechanism

Abstract

Rooted in a form of inexact supervision, complementary label learning (CLL) relieves the labeling burden of attaining definite categories for numerous training samples by depicting each of them through one or several incorrect categories. Although existing approaches adopt diverse network structures, learning paradigms and loss functions to facilitate CLL, developing a dependable classifier with the provided complementary labels remains challenging. To this end, a novel CLL method integrated with multi-view fusion and a semi-supervised labeling mechanism, called MVSSCLL, is proposed in this work. MVSSCLL is able to learn adaptively the label distribution of the training samples by leveraging a semi-supervised labeling mechanism. Simultaneously, a multi-view feature fusion approach following the consensus and complementary principles is also embedded. Such integration helps enhance the extraction of valuable information from multi-view feature data with complementary labels. Experimentally, MVSSCLL surpasses significantly the state-of-the-art methods. The maximum accuracy advantage over the second-best method reaches 43.11 %. The advancements made by MVSSCLL have greatly improved the performance of CLL without increasing labeling costs.