On Learning Vector Representations in Hierarchical Label Spaces

TL;DR

This paper introduces a novel method for learning vector representations of labels in hierarchical multi-label classification, leveraging label hierarchies and co-occurrence patterns to capture underlying label regularities.

Contribution

The paper presents a new approach to embed labels in vector space using hierarchical structures and co-occurrence data, enabling better understanding of label relationships.

Findings

The method effectively captures label regularities using hierarchy and co-occurrence.

Hierarchical information enhances the quality of learned label embeddings.

Representations depend on the label hierarchy used.

Abstract

An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. This paper addresses one such problem, namely how to exploit hierarchical structures over labels. We present a novel method to learn vector representations of a label space given a hierarchy of labels and label co-occurrence patterns. Our experimental results demonstrate qualitatively that the proposed method is able to learn regularities among labels by exploiting a label hierarchy as well as label co-occurrences. It highlights the importance of the hierarchical information in order to obtain regularities which facilitate analogical reasoning over a label space. We also experimentally illustrate the dependency of the learned representations on the label hierarchy.