Determinate node selection for semi-supervised classification oriented graph convolutional networks

Graph convolutional networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labelled nodes used in GCNs may lead to unstable generalisation performance of GCNs. In this paper, we propose an efficient method for the deterministic selection of labelled nodes: the determinate node selection (DNS) algorithm. The DNS algorithm identifies two categories of representative nodes in the graph through structural analysis of the leading tree information granules: typical nodes and divergent nodes. These labelled nodes are selected by exploring the structure of the graph and determining the ability of the nodes to represent the distribution of data within the graph. The DNS algorithm can be applied quite simply on GCNs, and a wide range of semi-supervised graph neural network models for node classification tasks. Through extensive experimentation, we have demonstrated that the incorporation of the DNS algorithm leads to a remarkable improvement in the average accuracy of the model and a significant decrease in the standard deviation simultaneously, as compared to the vanilla method without a DNS module.