arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.07671cs.LGcs.AI
收藏

边特征图注意力网络

Edge-Featured Graph Attention Network

School of Software(软件学院);Shanghai Jiao Tong University(上海交通大学)

Jun Chen, Haopeng Chen

摘要:

已经提出了许多神经网络架构来处理图结构数据上的学习任务。然而,这些模型中的大多数在学习过程中只关注节点特征。边缘特征通常起着与节点相似的重要作用,但这些模型往往忽略或简化了边缘特征。在本文中,我们提出了边特征图注意力网络,即EGAT,将图神经网络的使用扩展到具有节点和边特征的图上的学习任务。这些模型可以看作是图注意力网络(GATs)的扩展。通过改革模型结构和学习过程,新模型可以接受节点和边特征作为输入,将边信息纳入特征表示中,并以并行但相互的方式迭代节点和边特征。结果表明,我们的工作是非常有竞争力的其他节点分类方法,可以很好地应用于边特征图学习任务。

英文摘要:

Lots of neural network architectures have been proposed to deal with learning tasks on graph-structured data. However, most of these models concentrate on only node features during the learning process. The edge features, which usually play a similarly important role as the nodes, are often ignored or simplified by these models. In this paper, we present edge-featured graph attention networks, namely EGATs, to extend the use of graph neural networks to those tasks learning on graphs with both node and edge features. These models can be regarded as extensions of graph attention networks (GATs). By reforming the model structure and the learning process, the new models can accept node and edge features as inputs, incorporate the edge information into feature representations, and iterate both node and edge features in a parallel but mutual way. The results demonstrate that our work is highly competitive against other node classification approaches, and can be well applied in edge-featured graph learning tasks.

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。

↑