Variational Graph Recurrent Neural Networks

Abstract

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.

arXiv commentAccepted to Neural Information Processing Systems (NeurIPS2019)

Cited by in corpus (16)

• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• BayReL: Bayesian Relational Learning for Multi-omics Data Integration
• Relational State-Space Model for Stochastic Multi-Object Systems
• Spotting Silent Buffer Overflows in Execution Trace through Graph Neural Network Assisted Data Flow Analysis
• TD-GEN: Graph Generation With Tree Decomposition
• DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks
• Network-principled deep generative models for designing drug combinations as graph sets
• Semi-Implicit Stochastic Recurrent Neural Networks