Recent Advances in Label Distribution Learning

Dear Colleagues,

Label distribution learning (LDL) is a novel learning paradigm that introduces label distribution to describe the labeling information of one instance. Label distribution defines the relative importance degrees of all labels and is therefore well suited for machine learning problems with label ambiguity. In addition, label enhancement (LE) enables the application of LDL to binary labeled data by automatically recovering label distributions from binary labels, extending the applicability of LDL. Since LDL has found extensive applications in various fields, its advances have garnered widespread attention among the machine learning community. In this Special Issue “Recent Advances in Label Distribution Learning”, we would like to invite researchers to submit their works on the recent advances of LDL, including theory, methodology, applications, and beyond.

Prof. Dr. Xin Geng
Dr. Ning Xu
Prof. Dr. Liangxiao Jiang
Topic Editors