Graph Contrastive Learning with Augmentations
This work addresses the problem of limited self-supervised learning for graph neural networks, offering a framework that improves representation learning for graph data, though it appears incremental as it adapts contrastive learning from CNNs to GNNs.
The authors tackled the challenge of learning generalizable, transferable, and robust representations for graph-structured data by proposing GraphCL, a graph contrastive learning framework with four types of augmentations. The results showed that GraphCL achieved similar or better performance than state-of-the-art methods across semi-supervised, unsupervised, transfer learning, and adversarial attack settings, without tuning augmentation extents or using sophisticated architectures.
Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augmentations on multiple datasets, in four different settings: semi-supervised, unsupervised, and transfer learning as well as adversarial attacks. The results show that, even without tuning augmentation extents nor using sophisticated GNN architectures, our GraphCL framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods. We also investigate the impact of parameterized graph augmentation extents and patterns, and observe further performance gains in preliminary experiments. Our codes are available at https://github.com/Shen-Lab/GraphCL.