Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation (Extended Abstract)

Lu Bai, Yuhang Jiao, Lixin Cui, Luca Rossi, Yue Wang, Philip S. Yu, Edwin R. Hancock

Abstract: This paper proposes a novel Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. The main idea is to define a new quantum-inspired spatial graph convolution associated with pre-transformed fixed-sized aligned grid structures of graphs, in terms of quantum information propagation between grid vertices of each graph. We show that the proposed QSGCNN model can significantly reduce either the information loss or the notorious tottering problem arising in existing spatially-based Graph Convolutional Network (GCN) models. Experiments on benchmark graph datasets demonstrate the effectiveness of the proposed QSGCNN model.