Improving Subgraph Representation Learning via Multi-View Augmentation
This work addresses a gap in GNN-based subgraph representation learning for applications like molecular and cellular predictions, though it appears incremental as it extends existing augmentation techniques to a new context.
The paper tackled the problem of subgraph representation learning by developing a novel multi-view augmentation mechanism to improve model accuracy and efficiency, demonstrating superiority on real-world biological and physiological datasets.
Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-property relationships and collective cellular function. In particular, graph augmentation techniques have shown promising results in improving graph-based and node-based classification tasks. Still, they have rarely been explored in the existing GNN-based subgraph representation learning studies. In this study, we develop a novel multi-view augmentation mechanism to improve subgraph representation learning models and thus the accuracy of downstream prediction tasks. Our augmentation technique creates multiple variants of subgraphs and embeds these variants into the original graph to achieve highly improved training efficiency, scalability, and accuracy. Benchmark experiments on several real-world biological and physiological datasets demonstrate the superiority of our proposed multi-view augmentation techniques in subgraph representation learning.