HEAT: Hyperbolic Embedding of Attributed Networks

TL;DR

HEAT is a novel method for embedding attributed networks into hyperbolic space, effectively capturing hierarchical and attribute information to improve downstream task performance.

Contribution

It introduces the first hyperbolic embedding approach specifically designed for attributed networks, combining a modified random walk and hyperboloid learning algorithm.

Findings

HEAT outperforms existing hyperbolic embedding methods on several tasks.

Leveraging node attributes improves embedding quality.

The method generalizes to both attributed and unattributed networks.

Abstract

Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding these networks into hyperbolic space because it can naturally represent a network's hierarchical structure. However, existing hyperbolic embedding approaches cannot deal with attributed networks, in which nodes are annotated with additional attributes. These attributes might provide additional proximity information to constrain the representations of the nodes, which is important to learn high quality hyperbolic embeddings. To fill this gap, we introduce HEAT (Hyperbolic Embedding of ATributed networks), the first method for embedding attributed networks to a hyperbolic space. HEAT consists of 1) a modified random walk algorithm to obtain training samples that capture both topological and attribute similarity; and 2) a learning algorithm for learning hyperboloid embeddings from the obtained training samples. We show that by leveraging node attributes, HEAT can outperform a state-of-the-art Hyperbolic embedding algorithm on several downstream tasks. As a general embedding method, HEAT opens the door to hyperbolic manifold learning on a wide range of attributed and unattributed networks.