Gated Graph Pooling with Self-Loop for Graph Classification

Xiaolong Fan, Maoguo Gong, Hao Li, Yue Wu, Shanfeng WangIJCNN 2020 · OpenReview

Abstract

Graph classification is a practical problem in many different domains including bioinformatics, chemoinformatics, social network analysis, and etc. For the graph classification task, the existing graph neural network approaches usually generate graph features using graph pooling at each step. However, this strategy of pooling only at the current step ignores the impact of self-loop. To eliminate this limitation, we propose a novel self-loop graph pooling strategy that can utilize the node information of the current step and the graph representation information of the previous step to generate an effective representation for the graph classification task. Further to measure the importance of self-loop, we also develop a gated approach, gated graph pooling with self-loop, that utilizes the simple fusion gate to enhance the representation capacity of the model. We evaluate our model on common benchmark datasets and experimental results have demonstrated the superior performance improvement on predictive accuracy.
BibTeX
@inproceedings{fan2020gated,
  author = {Xiaolong Fan and Maoguo Gong and Hao Li and Yue Wu and Shanfeng Wang},
  title = {{Gated Graph Pooling with Self-Loop for Graph Classification}},
  booktitle = {IJCNN},
  year = {2020},
  url = {https://openreview.net/forum?id=Ezv9xKF21t},
}

Loading related content...

Figure