Hierarchical Model Selection for Graph Neural Netoworks
This addresses the challenge of selecting optimal GNNs for different graph data in node classification tasks, but it is incremental as it builds on existing GNN variants.
The paper tackles the problem of node classification on graph data by proposing a hierarchical model selection framework (HMSF) that selects appropriate graph neural network models based on graph indicators, achieving high performance across various graph types.
Node classification on graph data is a major problem, 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 which these GNN variants fail to perform well than other GNNs in the node classification task. This is because H2GCN has a feature thinning on graph data with high average degree, and CPF gives rise to a problem about label-propagation suitability. Accordingly, we propose a hierarchical model selection framework (HMSF) that selects an appropriate GNN model by analyzing the indicators of each graph data. In the experiment, we show that the model selected by our HMSF achieves high performance on node classification for various types of graph data.