Incorporating Siamese Network Structure into Graph Neural Network Article Swipe
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1088/1742-6596/2171/1/012023
Siamese network plays an important role in many artificial intelligence domains, but there requires more exploration of applying Siamese structure to graph neural network. This paper proposes a novel framework that incorporates Siamese network structure into Graph Neural Network (Siam-GNN). We use DropEdge as graph augmentation technique to generate new graphs. Besides, the strategy of constructing Siamese network’s paired inputs is also studied in our work. Notably, stopping gradient backpropagation one side in Siam-GNN is an important factor affecting the performance of model. We equip some graph neural networks with Siamese structure and evaluate these Siam-GNNs on several standard semi-supervised node classification datasets and achieve surprising improvement on almost every original graph neural network.
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1088/1742-6596/2171/1/012023
- https://iopscience.iop.org/article/10.1088/1742-6596/2171/1/012023/pdf
- OA Status
- diamond
- Cited By
- 2
- References
- 18
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4207007961