Angle-based hierarchical classification using exact label embedding

TL;DR

This paper introduces a novel angle-based hierarchical classification method that preserves label hierarchy, reduces hypothesis space complexity, and is computationally efficient, with proven theoretical properties and demonstrated advantages in document categorization.

Contribution

It proposes a new label embedding that maintains hierarchy exactly and develops an efficient angle-based classifier with theoretical guarantees.

Findings

Outperforms existing methods in simulations

Effective in large-scale document categorization

Theoretically proven properties of the new method

Abstract

Hierarchical classification problems are commonly seen in practice. However, most existing methods do not fully utilize the hierarchical information among class labels. In this paper, a novel label embedding approach is proposed, which keeps the hierarchy of labels exactly, and reduces the complexity of the hypothesis space significantly. Based on the newly proposed label embedding approach, a new angle-based classifier is developed for hierarchical classification. Moreover, to handle massive data, a new (weighted) linear loss is designed, which has a closed form solution and is computationally efficient. Theoretical properties of the new method are established and intensive numerical comparisons with other methods are conducted. Both simulations and applications in document categorization demonstrate the advantages of the proposed method.