Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
This addresses the challenge of graph data scarcity and robustness for users of graph neural networks, though it is incremental as it builds on existing GCN and variational inference techniques.
The paper tackles the problem of applying graph convolutional networks (GCNs) when no input graph is available and under adversarial attacks, by proposing a variational inference framework that jointly estimates graph posteriors and GCN parameters, resulting in outperforming state-of-the-art methods on semi-supervised classification tasks.
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.