Review on hierarchical learning methods for large-scale classification task

Abstract

Hierarchical classification is a task that uses hierarchy of categories in data. It can handle large-scale data. In recent years, significant research has emerged in this field, which is receiving increasingly more attention. In this paper, we first introduce the definition of hierarchical classification and thereafter review the important studies on several basic issues in large-scale hierarchical classification tasks based on different problem-solving strategies. First, we define the hierarchy formally and introduce some hierarchical evaluation metrics. Second, we explain how to construct the hierarchy, how to learn classifiers and perform feature selection using the information in the hierarchy, and how to design stopping strategies and introduce some representative studies on each issue. Finally, we summarize the features of large-scale hierarchical classification task and discuss the possible future work in this field.