注意力感知的边−节点交换图神经网络模型

Attention aware edge-node exchange graph neural network

提出了一种注意力感知的边-节点交换图神经网络(attention aware edge-node exchange graph neural network,AENN)模型,在图结构化数据表示框架下,使用边-节点切换卷积的图神经网络算法进行图编码,用于半监督分类和回归分析。AENN是一种通用的图编码框架,用于将图节点和边嵌入一个统一的潜在特征空间。具体地,基于原始无向图,不断切换边与节点的卷积,并在卷积过程中通过注意力机制分配不同邻居的权重,从而实现特征传播。在3个数据集上的实验研究表明,所提方法较已有方法在半监督分类和回归分析中具有明显的性能提升。

An attention aware edge-node exchange graph neural network(AENN)model was proposed,which used edge-node switched convolutional graph neural network method for graph encoding in a graph structured data repre-sentation framework for semi supervised classification and regression analysis.AENN is an universal graph encoding framework for embedding graph nodes and edges into a unified latent feature space.Specifically,based on the origi-nal undirected graph,the convolution between edges and nodes was continuously switched,and during the convolu-tion process,attention mechanisms were used to assign weights to different neighbors,thereby achieving feature propagation.Experimental studies on three datasets show that the proposed method has significant performance im-provements in semi-supervised classification and regression analysis compared to existing methods.