arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2107.01495cs.LGcs.AIcs.SI
收藏

非属性图上图神经网络的位置和结构节点特征

On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

Emory University(埃默里大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Purdue University(普渡大学)

Hejie Cui, Zijie Lu, Pan Li, Carl Yang

摘要:

图神经网络(GNN)已被广泛用于各种与图相关的问题,例如节点分类和图分类,其中主要在自然节点特征可用时建立优越的性能。然而,没有自然节点特征的GNN如何工作还没有很好的理解,特别是关于构建人工节点的各种方法。在本文中,我们指出了两种类型的人工节点特征,即,位置和结构节点特征,并提供关于为什么它们中的每一个更适合于某些任务的见解,即,位置节点分类、结构节点分类和图形分类。在10个基准数据集上进行的大量实验结果验证了我们的见解,从而为非属性图上GNN的不同人工节点特征之间的选择提供了实用指南。该代码可在https://github.com/zjzijielu/gnn-positional-structural-node-features上获得。

英文摘要:

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones. In this paper, we point out the two types of artificial node features, i.e., positional and structural node features, and provide insights on why each of them is more appropriate for certain tasks, i.e., positional node classification, structural node classification, and graph classification. Extensive experimental results on 10 benchmark datasets validate our insights, thus leading to a practical guideline on the choices between different artificial node features for GNNs on non-attributed graphs. The code is available at https://github.com/zjzijielu/gnn-positional-structural-node-features.

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。

↑