Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
复制标题
DOI：
10.1609/aaai.v35i5.16563
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Li Sun;Zhongbao Zhang;Jiawei Zhang;Feiyang Wang;Hao Peng;Sen Su;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Li Sun;Zhongbao Zhang;Jiawei Zhang;Feiyang Wang;Hao Peng;Sen Su;Philip S. Yu
学习图的表示在广泛的下游应用程序中起着关键作用。本文从表征空间、建模动态性和建模不确定性三个方面总结了前人研究的局限性。为了弥补这一差距，我们首次提出在双曲空间中学习动态图表示，其目的是推断随机节点表示。在双曲空间中，我们提出了一种新的双曲变分图神经网络，称为HVGNN。特别是，为了对动态建模，我们引入了一种基于理论基础时间编码方法的时间GNN （TGNN）。为了模拟不确定性，我们设计了一个基于所提出的TGNN的双曲图变分自编码器来生成双曲正态分布的随机节点表示。此外，我们引入了一种双曲正态分布的可重新参数化采样算法，以实现基于梯度的HVGNN学习。大量实验表明，HVGNN在实际数据集上的性能优于最先进的基线。
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.