A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification

TL;DR

This paper introduces the first fully hyperbolic neural model for hierarchical multi-class classification, effectively capturing class hierarchies and relations while reducing parameters and integrating seamlessly with Euclidean layers.

Contribution

It proposes a novel fully hyperbolic model for multi-label classification that operates entirely in hyperbolic space, capturing hierarchical relations more effectively.

Findings

Performs on par with state-of-the-art methods

Reduces parameter size significantly

Captures implicit hyponymic relations

Abstract

Label inventories for fine-grained entity typing have grown in size and complexity. Nonetheless, they exhibit a hierarchical structure. Hyperbolic spaces offer a mathematically appealing approach for learning hierarchical representations of symbolic data. However, it is not clear how to integrate hyperbolic components into downstream tasks. This is the first work that proposes a fully hyperbolic model for multi-class multi-label classification, which performs all operations in hyperbolic space. We evaluate the proposed model on two challenging datasets and compare to different baselines that operate under Euclidean assumptions. Our hyperbolic model infers the latent hierarchy from the class distribution, captures implicit hyponymic relations in the inventory, and shows performance on par with state-of-the-art methods on fine-grained classification with remarkable reduction of the parameter size. A thorough analysis sheds light on the impact of each component in the final prediction and showcases its ease of integration with Euclidean layers.