Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings

Abstract

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.

Cited by in corpus (9)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
• Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
• Node Copying: A Random Graph Model for Effective Graph Sampling
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Dual GNNs: Graph Neural Network Learning with Limited Supervision
• Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks
• Training Graph Neural Networks by Graphon Estimation