历安毛子代枚大学 (3)图卷积网络 XIDIAN UNIVERSITY 基于谱的卷积图神经网络 2 FAST APPROXIMATE CONVOLUTIONS ON GRAPHS In this section,we provide theoretical motivation for a specific graph-based neural network model f(X,A)that we will use in the rest of this paper.We consider a multi-layer Graph Convolutional Network(GCN)with the following layer-wise propagation rule: H+)=o(DAD-H0WO)） (2) Here,A=A+IN is the adjacency matrix of the undirected graph with added self-connections. IN is the identity matrix,DAjand W(is a layer-specific trainable weight matrix.( denotes an activation function,such as the ReLU()=max(0,).H(ERND is the matrix of ac- tivations in theh layer;H()=X.In the following,we show that the form of this propagation rule can be motivatedvia a first-order approximation of localized spectral filters on graphs (Hammond et al.,2011;Defferrard et al.,2016). T.N.Kipf and M.Welling.Semi-supervised classification with graph convolutional networks.In ICLR.2016. （3）图卷积网络 11 基于谱的卷积图神经网络 T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2016