I. Introduction
There have been increasing interests to generalize convolutional neural networks (CNNs) [1]–[5] to graph domains. These neural networks on graphs are now widely known as graph convolutional networks (GCNs) [6]–[10], and have been proven effective to extract highly meaningful statistical features from graph structures [11]. The aim of this work is to develop novel GCN models to learn rich features of local-level vertices for graph classification.