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.
万方数据
