Graph Mixed Random Network Based on PageRank

In recent years, graph neural network algorithm (GNN) for graph semi-supervised classification has made great progress. However, in the task of node classification, the neighborhood size is often difficult to expand. The propagation of nodes always only considers the nearest neighbor nodes. Some algorithms usually approximately classify by message passing between direct (single-hop) neighbors. This paper proposes a simple and effective method, named Graph Mixed Random Network Based on PageRank (PMRGNN) to solve the above problems. In PMRGNN, we design a PageRank-based random propagation strategy for data augmentation. Then, two feature extractors are used in combination to supplement the mutual information between features. Finally, a graph regularization term is designed, which can find more useful information for classification results from neighbor nodes to improve the performance of the model. Experimental results on graph benchmark datasets show that the method of this paper outperforms several recently proposed GNN baselines on the semi-supervised node classification. In the research of over-smoothing and generalization, PMRGNN always maintains better performance. In classification visualization, it is more intuitive than other classification methods.