arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.07518cs.LGstat.ML
收藏

Self-Enhanced GNN:使用模型输出改进图神经网络

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

The Chinese University of Hong Kong(香港中文大学);Southern University of Science and Technology(南方科技大学)

Han Yang, Xiao Yan, Xinyan Dai, Yongqiang Chen, James Cheng

摘要:

图神经网络(GNNs)由于其在基于图的任务上的优异性能而受到广泛关注。然而,现有的GNN研究集中在设计更有效的模型,而没有考虑输入数据的质量。在本文中,我们提出了自增强GNN(SEG),它使用现有GNN模型的输出来提高输入数据的质量,以获得更好的半监督节点分类性能。由于图数据由拓扑和节点标签组成,我们从这两个角度提高了输入数据质量。对于拓扑结构,我们观察到,当类间边缘(连接不同类的节点)的比率较低时,可以实现更高的分类精度,并提出拓扑结构更新以删除类间边缘并添加类内边缘。对于节点标签,我们提出了训练节点增强,它使用现有GNN模型预测的标签来扩大训练集。SEG是一个通用框架,可以很容易地与现有的GNN模型相结合。实验结果验证了SEG在不同数据集上一致地提高了GCN,GAT和SGC等知名GNN模型的性能。

英文摘要:

Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on designing more effective models without considering much about the quality of the input data. In this paper, we propose self-enhanced GNN (SEG), which improves the quality of the input data using the outputs of existing GNN models for better performance on semi-supervised node classification. As graph data consist of both topology and node labels, we improve input data quality from both perspectives. For topology, we observe that higher classification accuracy can be achieved when the ratio of inter-class edges (connecting nodes from different classes) is low and propose topology update to remove inter-class edges and add intra-class edges. For node labels, we propose training node augmentation, which enlarges the training set using the labels predicted by existing GNN models. SEG is a general framework that can be easily combined with existing GNN models. Experimental results validate that SEG consistently improves the performance of well-known GNN models such as GCN, GAT and SGC across different datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑