Label Distribution Learning by Optimal Transport

Label distribution learning (LDL) is a novel learning paradigm to deal with some real-world applications, especially when we care more about the relative importance of different labels in description of an instance. Although some approaches have been proposed to learn the label distribution, they could not explicitly learn and leverage the label correlation, which plays an importance role in LDL. In this paper, we propose an approach to learn the label distribution and exploit label correlations simultaneously based on the Optimal Transport (OT) theory. The problem is solved by alternatively learning the transportation (hypothesis) and ground metric (label correlations). Besides, we provide perhaps the first data-dependent risk bound analysis for label distribution learning by Sinkhorn distance, a commonly-used relaxation for OT distance. Experimental results on real-world datasets comparing with several state-of-the-art methods validate the effectiveness of our approach.

Authors

• Peng Zhao Nanjing University
• Zhi-Hua Zhou Nanjing University

Keywords

No keywords are indexed for this paper.