Hop-hop relation-aware graph neural networks

Abstract

Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs. In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs. HHR-GNN learns a personalized receptive field for each node by leveraging knowledge graph embedding to learn relation scores between the central node’s representations at different hops. In neighborhood aggregation, our model simultaneously allows for hop-aware projection and aggregation. This mechanism enables the central node to learn a hop-wise neighborhood mixing that can be applied to both homogeneous and heterogeneous graphs. Experimental results on five benchmarks show the competitive performance of our model compared to state-of-the-art GNNs, e.g., up to 13K faster in terms of time cost per training epoch on large heterogeneous graphs.

Publication
arXiv preprint arXiv:2012.11147
Li Zhang
Li Zhang
PhD Student (now an Associate Lecturer at University College London)
Yan Ge
Yan Ge
PhD Student (now a Lecturer in Financial Technology at University of Bristol)
Haiping Lu
Haiping Lu
Director of the UK Open Multimodal AI Network, Professor of Machine Learning, and Head of AI Research Engineering

I am a Professor of Machine Learning. I develop translational multimodal AI technologies for advancing healthcare and scientific discovery.