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 GNN model, called CS-GNN, is then designed 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.
翻译：图表神经网络(GNNs)被广泛用于在图表数据上进行演示学习,但是,对于图形数据实际取得多少实绩全球NNs的情况了解有限,本文介绍了环绕背景的GNN框架,并提出了衡量从图表数据中获得信息的数量和质量的两种光滑度度度度量标准。然后设计了一个新的GNN(称为CS-GNN)模型,目的是根据图表的光度值改进图形信息的使用。 CS-GNN(GNN)显示,在不同类型的真实图表中,CS-GNN的性能优于现有方法。
相关内容
微信扫码咨询专知VIP会员