On Learning Vector Representations in Hierarchical Label Spaces
This work addresses the challenge of improving multi-label classification for applications with hierarchical label structures, though it appears incremental as it builds on existing representation learning approaches.
The paper tackles the problem of capturing label patterns in multi-label classification by exploiting hierarchical structures over labels, presenting a novel method to learn vector representations from label hierarchies and co-occurrence patterns, with experimental results demonstrating the method's ability to learn regularities and facilitate analogical reasoning.
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.