Hierarchical Model Selection for Graph Neural Networks

Abstract

Node classification on graph data is a major problem in machine learning, and various graph neural networks (GNNs) have been proposed. Variants of GNNs such as H2GCN and CPF outperform graph convolutional networks (GCNs) by improving on the weaknesses of the traditional GNN. However, there are some graph data in which these GNN variants fail to perform well than other GNNs in the node classification task. This is because H2GCN has similar feature values on graph data with a high average degree, and CPF gives rise to a problem with label-propagation suitability. Accordingly, we propose a hierarchical model selection framework (HMSF) that selects an appropriate GNN model to predict the class of nodes for each graph data. HMSF uses average degree and edge homophily ratio as indicators to decide the useful model based on our analyses. In the experiment, we show that the model selected by our HMSF achieves high performance on node classification for various types of graph data.