Two-stage Training of Graph Neural Networks for Graph Classification

TL;DR

This paper introduces a two-stage training framework for graph neural networks using triplet loss, significantly improving graph classification accuracy across multiple models and datasets.

Contribution

It proposes a generic two-stage training approach that enhances GNN capacity utilization and accuracy, applicable to any GNN model for graph classification.

Findings

Consistent accuracy improvements up to 5.4% points across 12 datasets.

Effective enhancement of GNN capacity utilization.

Compatibility with multiple GNN models.

Abstract

Graph neural networks (GNNs) have received massive attention in the field of machine learning on graphs. Inspired by the success of neural networks, a line of research has been conducted to train GNNs to deal with various tasks, such as node classification, graph classification, and link prediction. In this work, our task of interest is graph classification. Several GNN models have been proposed and shown great accuracy in this task. However, the question is whether usual training methods fully realize the capacity of the GNN models. In this work, we propose a two-stage training framework based on triplet loss. In the first stage, GNN is trained to map each graph to a Euclidean-space vector so that graphs of the same class are close while those of different classes are mapped far apart. Once graphs are well-separated based on labels, a classifier is trained to distinguish between different classes. This method is generic in the sense that it is compatible with any GNN model. By adapting five GNN models to our method, we demonstrate the consistent improvement in accuracy and utilization of each GNN's allocated capacity over the original training method of each model up to 5.4\% points in 12 datasets.