Kavli Affiliate: Yi Zhou
| First 5 Authors: Yili Shen, Jiaxu Yan, Cheng-Wei Ju, Jun Yi, Zhou Lin
| Summary:
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.
| Search Query: ArXiv Query: search_query=au:”Yi Zhou”&id_list=&start=0&max_results=10