Measuring and Improving the Use of Graph Information in Graph Neural Networks
Abstract
Graph neural networks (GNNs) have been widely used for representation learning on graph data. However, there is limited understanding on how much performance GNNs actually gain from graph data. This paper introduces a context-surrounding GNN framework and proposes two smoothness metrics to measure the quantity and quality of information obtained from graph data. A new, improved GNN model, called CS-GNN, is then devised to improve the use of graph information based on the smoothness values of a graph. CS-GNN is shown to achieve better performance than existing methods in different types of real graphs.
Cite
Text
Hou et al. "Measuring and Improving the Use of Graph Information in Graph Neural Networks." International Conference on Learning Representations, 2020.Markdown
[Hou et al. "Measuring and Improving the Use of Graph Information in Graph Neural Networks." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/hou2020iclr-measuring/)BibTeX
@inproceedings{hou2020iclr-measuring,
title = {{Measuring and Improving the Use of Graph Information in Graph Neural Networks}},
author = {Hou, Yifan and Zhang, Jian and Cheng, James and Ma, Kaili and Ma, Richard T. B. and Chen, Hongzhi and Yang, Ming-Chang},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/hou2020iclr-measuring/}
}