Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs

Authors

  • Li Sun Beijing University of Posts and Telecommunications
  • Zhongbao Zhang Beijing University of Posts and Telecommunications
  • Jiawei Zhang Florida State University
  • Feiyang Wang Beijing University of Posts and Telecommunications
  • Hao Peng Beihang University
  • Sen Su Beijing University of Posts and Telecommunications
  • Philip S. Yu University of Illinois at Chicago

Keywords:

Graph Mining, Social Network Analysis & Community, Representation Learning

Abstract

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic graph representations in hyperbolic space, for the first time, which aims to infer stochastic node representations. Working with hyperbolic space, we present a novel Hyperbolic Variational Graph Neural Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach. To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions. Furthermore, we introduce a reparameterisable sampling algorithm for the hyperbolic normal distribution to enable the gradient-based learning of HVGNN. Extensive experiments show that HVGNN outperforms state-of-the-art baselines on real-world datasets.

Downloads

Published

2021-05-18

How to Cite

Sun, L., Zhang, Z., Zhang, J., Wang, F., Peng, H., Su, S., & Yu, P. . S. (2021). Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4375-4383. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16563

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management