Pre-Training Graph Neural Networks for Generic Structural Feature Extraction

TL;DR

This paper introduces a pre-training framework for graph neural networks that captures transferable structural features from synthetic graphs, reducing the need for labeled data and domain-specific features in downstream tasks.

Contribution

The paper proposes a novel pre-training approach for GNNs using synthetic graphs and three structural tasks, improving transferability and reducing data requirements.

Findings

Pre-trained GNNs outperform training from scratch on multiple tasks.

The framework requires less labeled data for effective performance.

Significant improvements observed across node, link, and graph level tasks.

Abstract

Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framework that captures generic graph structural information that is transferable across tasks. Our framework can leverage the following three tasks: 1) denoising link reconstruction, 2) centrality score ranking, and 3) cluster preserving. The pre-training procedure can be conducted purely on the synthetic graphs, and the pre-trained GNN is then adapted for downstream applications. With the proposed pre-training procedure, the generic structural information is learned and preserved, thus the pre-trained GNN requires less amount of labeled data and fewer domain-specific features to achieve high performance on different downstream tasks. Comprehensive experiments demonstrate that our proposed framework can significantly enhance the performance of various tasks at the level of node, link, and graph.