Variational Graph Recurrent Neural Networks
Variational Graph Recurrent Neural Networks
复制标题
DOI：
--
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Ehsan Hajiramezanali;Arman Hasanzadeh;N. Duffield;K. Narayanan;Mingyuan Zhou;Xiaoning Qian
中科院分区：
文献类型：
--
作者：
Ehsan Hajiramezanali;Arman Hasanzadeh;N. Duffield;K. Narayanan;Mingyuan Zhou;Xiaoning Qian
图结构化数据的表示学习主要是在静态图环境中进行的，而对动态图建模的研究仍然很少。在本文中，我们开发了一种新的分层变分模型，引入额外的潜在随机变量，共同建模的图递归神经网络（GRNN）的隐藏状态，以捕捉动态图中的拓扑结构和节点属性的变化。我们认为，在这种变分GRNN（VGRNN）中使用高级别的潜在随机变量可以更好地捕捉动态图中观察到的潜在变化以及节点潜在表示的不确定性。随着半隐式变分推理开发这个新的VGRNN架构（SI-VGRNN），我们表明，灵活的非高斯潜在表示可以进一步帮助动态图分析任务。我们对多个真实世界动态图数据集的实验表明，SI-VGRNN和VGRNN在动态链接预测方面始终优于现有的基线和最先进的方法。
Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant. In this paper, we develop a novel hierarchical variational model that introduces additional latent random variables to jointly model the hidden states of a graph recurrent neural network (GRNN) to capture both topology and node attribute changes in dynamic graphs. We argue that the use of high-level latent random variables in this variational GRNN (VGRNN) can better capture potential variability observed in dynamic graphs as well as the uncertainty of node latent representation. With semi-implicit variational inference developed for this new VGRNN architecture (SI-VGRNN), we show that flexible non-Gaussian latent representations can further help dynamic graph analytic tasks. Our experiments with multiple real-world dynamic graph datasets demonstrate that SI-VGRNN and VGRNN consistently outperform the existing baseline and state-of-the-art methods by a significant margin in dynamic link prediction.