How Neural Processes Improve Graph Link Prediction

Abstract

We propose a meta-learning approach with graph neural networks for link prediction: Neural Processes for Graph Neural Networks (NPGNN), which can not only perform both transductive and inductive learning tasks, but also generalize well when only training on a small subgraph. The key idea is to assume the node embeddings follow a Gaussian Process parameterised by graph neural networks and then use a meta-learning framework to pass information from the subgraph to the complete graph. Experiments on real-world citation networks are conducted to validate our model, where the results suggest that the proposed method achieves stronger performance compared to other state-of-the-art models.