Variational Graph Recurrent Neural Networks

08/26/2019
by   Ehsan Hajiramezanali, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/28/2019

Semi-Implicit Stochastic Recurrent Neural Networks

Stochastic recurrent neural networks with latent random variables of com...
research
09/01/2020

Stochastic Graph Recurrent Neural Network

Representation learning over graph structure data has been widely studie...
research
10/02/2019

Graph Generation with Variational Recurrent Neural Network

Generating graph structures is a challenging problem due to the diverse ...
research
06/09/2022

Accurate Node Feature Estimation with Structured Variational Graph Autoencoder

Given a graph with partial observations of node features, how can we est...
research
10/31/2020

Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference

Efficient modeling of relational data arising in physical, social, and i...
research
08/10/2021

Regularized Sequential Latent Variable Models with Adversarial Neural Networks

The recurrent neural networks (RNN) with richly distributed internal sta...
research
02/07/2019

Graph Classification with Recurrent Variational Neural Networks

We address the problem of graph classification based only on structural ...

Please sign up or login with your details

Forgot password? Click here to reset