Enhancing Hyperbolic Graph Embeddings via Contrastive Learning

TL;DR

This paper introduces a novel hyperbolic graph contrastive learning framework that leverages multiple hyperbolic spaces and a position consistency constraint to improve node representations and outperform existing methods.

Contribution

It proposes HGCL, a contrastive learning approach in hyperbolic space that captures hierarchical structures and utilizes unlabelled data effectively.

Findings

HGCL outperforms competing methods on node classification tasks.

The use of multiple hyperbolic spaces enhances representation learning.

Hyperbolic position consistency improves contrastive learning in hyperbolic space.

Abstract

Recently, hyperbolic space has risen as a promising alternative for semi-supervised graph representation learning. Many efforts have been made to design hyperbolic versions of neural network operations. However, the inspiring geometric properties of this unique geometry have not been fully explored yet. The potency of graph models powered by the hyperbolic space is still largely underestimated. Besides, the rich information carried by abundant unlabelled samples is also not well utilized. Inspired by the recently active and emerging self-supervised learning, in this study, we attempt to enhance the representation power of hyperbolic graph models by drawing upon the advantages of contrastive learning. More specifically, we put forward a novel Hyperbolic Graph Contrastive Learning (HGCL) framework which learns node representations through multiple hyperbolic spaces to implicitly capture the hierarchical structure shared between different views. Then, we design a hyperbolic position consistency (HPC) constraint based on hyperbolic distance and the homophily assumption to make contrastive learning fit into hyperbolic space. Experimental results on multiple real-world datasets demonstrate the superiority of the proposed HGCL as it consistently outperforms competing methods by considerable margins for the node classification task.