Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks

TL;DR

This paper introduces Pairwise Half-graph Discrimination (PHD), a simple self-supervised pre-training method for graph neural networks that improves graph-level representation learning and outperforms existing strategies on multiple tasks.

Contribution

The paper proposes PHD, a novel graph-level self-supervised pre-training strategy that discriminates whether two half-graphs originate from the same source, enhancing transferability and robustness.

Findings

PHD achieves comparable or better performance than state-of-the-art methods on 13 graph classification tasks.

Combining PHD with node-level strategies yields notable improvements.

Visualization shows PHD helps the model learn graph-level features like molecular scaffolds.

Abstract

Self-supervised learning has gradually emerged as a powerful technique for graph representation learning. However, transferable, generalizable, and robust representation learning on graph data still remains a challenge for pre-training graph neural networks. In this paper, we propose a simple and effective self-supervised pre-training strategy, named Pairwise Half-graph Discrimination (PHD), that explicitly pre-trains a graph neural network at graph-level. PHD is designed as a simple binary classification task to discriminate whether two half-graphs come from the same source. Experiments demonstrate that the PHD is an effective pre-training strategy that offers comparable or superior performance on 13 graph classification tasks compared with state-of-the-art strategies, and achieves notable improvements when combined with node-level strategies. Moreover, the visualization of learned representation revealed that PHD strategy indeed empowers the model to learn graph-level knowledge like the molecular scaffold. These results have established PHD as a powerful and effective self-supervised learning strategy in graph-level representation learning.