Subgraph representation learning based on Graph Neural Network (GNN) has broad applications in chemistry and biology, such as molecule property prediction and gene collaborative function prediction. On the other hand, graph augmentation techniques have shown promising results in improving graph-based and node-based classification tasks but are rarely explored in the GNN-based subgraph representation learning literature. In this work, we developed a novel multiview augmentation mechanism to improve subgraph representation learning and thus the accuracy of downstream prediction tasks. The augmentation technique creates multiple variants of subgraphs and embeds these variants into the original graph to achieve both high training efficiency, scalability, and improved accuracy. Experiments on several real-world subgraph benchmarks demonstrate the superiority of our proposed multi-view augmentation techniques.

本研究提出一种新颖的多视角扩充机制，以改进基于子图表征学习模型的训练效果和下游预测任务的准确性，在多个真实世界的生物和生理数据集上的基准实验表明，该扩充技术相较于现有的图神经网络表征学习研究具有更好的训练效率、可扩展性和准确度。

通过多视角增强提高子图表征学习