Timezone: »

 
Poster
Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
Pantelis Elinas · Edwin Bonilla · Louis Tiao

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #28
in Poster Session 1 »

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.

Author Information

Pantelis Elinas (CSIRO's Data61)
Edwin Bonilla (CSIRO's Data61)
Louis Tiao (University of Sydney)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors