Uncertainty-Aware Prediction for Graph Neural Networks

Thanks to graph neural networks (GNNs), semi-supervised node classification has shown the state-of-the-art performance in graph data. However, GNNs do not consider any types of uncertainties associated with the class probabilities to minimize risk due to misclassification under uncertainty in real life. In this work, we propose a Bayesian deep learning framework reflecting various types of uncertainties for classification predictions by leveraging the powerful modeling and learning capabilities of GNNs. We considered multiple uncertainty types in both deep learning (DL) and belief/evidence theory domains. We treat the predictions of a Bayesian GNN (BGNN) as nodes' multinomial subjective opinions in a graph based on Dirichlet distributions where each belief mass is a belief probability of each class. By collecting evidence from the given labels of training nodes, the BGNN model is designed for accurately predicting probabilities of each class and detecting out-of-distribution. We validated the outperformance of the proposed BGNN, compared to the state-of-the-art counterparts in terms of the accuracy of node classification prediction and out-of-distribution detection based on six real network datasets.