Variational Graph Convolutional Networks

Photo by Clint Adair on Unsplash


We propose a framework that lifts the capabilities of graph convolutional networks (GCNs) to scenarios where no input graph is given and increases their robustness to adversarial attacks. We formulate a joint probabilistic model that considers a prior distribution over graphs along with a GCN-based likelihood and develop a stochastic variational inference algorithm to estimate the graph posterior and the GCN parameters jointly. To address the problem of propagating gradients through latent variables drawn from discrete distributions, we use their continuous relaxations known as Concrete distributions. We show that, on real datasets, our approach can outperform state-of-the-art Bayesian and non-Bayesian graph neural network algorithms on the task of semi-supervised classification in the absence of graph data and when the network structure is subjected to adversarial perturbations.

Presented at the NeurIPS2019 Workshop on Graph Representation Learning. Vancouver, Canada, 2019 as Outstanding Contribution Talk
Louis Tiao
Louis Tiao
PhD Candidate

Probabilistic machine learning and artificial intelligence.

comments powered by Disqus