Graph convolutional networks fusing motif-structure information

With the advent of the wave of big data, the generation of more and more graph data brings great pressure to the traditional deep learning model. The birth of graph neural network fill the gap of deep learning in graph data. At present, graph convolutional networks (GCN) have surpassed traditional methods such as network embedding in node classification. However, The existing graph convolutional networks only consider the edge structure information of first-order neighbors as the bridge of information aggregation in a convolution operation, which undoubtedly loses the higher-order structure information in complex networks. In order to capture more abundant information of the graph topology and mine the higher-order information in complex networks, we put forward our own graph convolutional networks model fusing motif-structure information. By identifying the motif-structure in the network, our model fuses the motif-structure information of nodes to study the aggregation feature weights, which enables nodes to aggregate higher-order network information, thus improving the capability of GCN model. Finally, we conduct node classification experiments in several real networks, and the experimental results show that the GCN model fusing motif-structure information can improve the accuracy of node classification.