Label Distribution Learning Based on Square Root Pearson

Abstract

Label distribution learning is a gradually emerging field of learning that can address label ambiguity. In a sense, label distribution learning includes common single-label learning and multi-label learning with broader applicability. For each instance, label distribution learning uses the label distribution to reflect the individual label importance. Previous studies have shown that label distribution learning is an effective method to address label ambiguity. In order to strengthen the learning performance and make the prediction of the distribution more accurate, this paper proposes a label distribution learning algorithm called SRPLDL. We propose a metric called the Square Root Pearson, and then we build our learning model on the basis of this metric. Comparative experiments on 11 real label distribution datasets prove that the SRPLDL algorithm can solve the label distribution learning problem and outperforms other algorithms.