HEAT: Hyperbolic Embedding of Attributed Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Authors

Colleges, School and Institutes

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 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 overcome this gap we propose HEAT (Hyperbolic Embedding of Attributed Networks). HEAT first extracts training samples from the original graph capturing both topological and attribute similarity and then learns a hyperboloid embedding using full Riemannian Stochastic Gradient Descent. We show that HEAT can outperform other network embedding algorithms 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.

Details

Original languageEnglish
Title of host publicationIntelligent Data Engineering and Automated Learning, IDEAL 2020
Subtitle of host publication 21st International Conference, Proceedings
Publication statusAccepted/In press - 5 Aug 2020
Event21st International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020 - Guimaraes, Portugal
Duration: 4 Nov 20206 Nov 2020

Conference

Conference21st International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020
CountryPortugal
CityGuimaraes
Period4/11/206/11/20

Keywords

  • Network embedding, Hyperbolic embedding, Random walk