Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks
This addresses a specific bottleneck in graph neural networks for node classification tasks, offering an incremental improvement over existing methods.
The paper tackles the problem of graph neural networks (GNNs) failing to directly characterize and leverage structural information for node classification, proposing a method that uses an i-hop adjacency matrix adjusted with information gain ratio and feature duplication, resulting in outperforming GCN, H2GCN, and GCNII in average accuracies on benchmark datasets.
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 features 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: (i) structural features in the matrix are selected based on the IGR, and (ii) the selected features in (i) for each node are duplicated and combined flexibly. In an experiment, we show that our MSI-GNN outperforms GCN, H2GCN, and GCNII in terms of average accuracies in benchmark graph datasets.