Hierarchical Model Selection for Graph Neural Netoworks

TL;DR

This paper introduces a hierarchical model selection framework (HMSF) that dynamically chooses the most suitable GNN model for node classification tasks based on graph data characteristics, improving performance across diverse datasets.

Contribution

The paper proposes a novel hierarchical model selection framework (HMSF) that analyzes graph indicators to select optimal GNN models, addressing limitations of existing variants.

Findings

HMSF achieves high node classification accuracy across various graph datasets.

The framework effectively addresses weaknesses of H2GCN and CPF models.

Model selection based on graph indicators improves GNN performance.

Abstract

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.