GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training

TL;DR

GCC is a self-supervised pre-training framework for graph neural networks that captures universal structural properties, enabling transferability and improved performance across diverse graph tasks and datasets.

Contribution

The paper introduces GCC, a novel contrastive pre-training method for GNNs that learns transferable structural representations across multiple networks.

Findings

GCC pre-training achieves competitive or superior results compared to task-specific models.

Pre-training on diverse datasets enhances transferability and generalization.

GCC demonstrates effectiveness across various graph learning tasks and datasets.

Abstract

Graph representation learning has emerged as a powerful technique for addressing real-world problems. Various downstream graph learning tasks have benefited from its recent developments, such as node classification, similarity search, and graph classification. However, prior arts on graph representation learning focus on domain specific problems and train a dedicated model for each graph dataset, which is usually non-transferable to out-of-domain data. Inspired by the recent advances in pre-training from natural language processing and computer vision, we design Graph Contrastive Coding (GCC) -- a self-supervised graph neural network pre-training framework -- to capture the universal network topological properties across multiple networks. We design GCC's pre-training task as subgraph instance discrimination in and across networks and leverage contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations. We conduct extensive experiments on three graph learning tasks and ten graph datasets. The results show that GCC pre-trained on a collection of diverse datasets can achieve competitive or better performance to its task-specific and trained-from-scratch counterparts. This suggests that the pre-training and fine-tuning paradigm presents great potential for graph representation learning.