Multi-Duplicated Characterization of Graph Structures Using Information Gain Ratio for Graph Neural Networks

Various graph neural networks (GNNs) have been proposed to solve node classification tasks in machine learning for graph data. GNNs use the structural information of graph data by aggregating the feature vectors of neighboring nodes. However, they fail to directly characterize and leverage the structural information. In this paper, we propose multi-duplicated characterization of graph structures using information gain ratio (IGR) for GNNs (MSI-GNN), which enhances the performance of node classification by using an i-hop adjacency matrix as the structural information of the graph data. In MSI-GNN, the i-hop adjacency matrix is adaptively adjusted by two methods: 1) structural features in the matrix are selected based on the information gain ratio and occurrence filter; and 2) the selected features in each node are duplicated and combined flexibly. Extensive experiments show that our MSI-GNN outperforms GCN, H2GCN, and GCNII in terms of average accuracies in benchmark graph datasets.