Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks

TL;DR

This paper introduces MSI-GNN, a novel method that enhances graph neural networks by adaptively selecting and duplicating structural features based on information gain ratio, leading to improved node classification accuracy.

Contribution

The paper proposes a new multi-duplicated characterization method using IGR for GNNs, which adaptively adjusts structural features to improve performance.

Findings

MSI-GNN outperforms GCN, H2GCN, and GCNII in benchmark datasets.

Adaptive feature selection based on IGR improves node classification.

Duplicating selected features enhances structural information utilization.

Abstract

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.