Dynamic depth-width optimization for capsule graph convolutional network

<正>1 Introduction Encouraged by the success of Convolutional Neural Networks(CNNs),many studies [1],known as Graph Convolutional Networks (GCNs),borrowed the idea of convolution and redefined it for graph data.In graph-level classification tasks,Classic GCN methods [2,3] generate graph embeddings based on the learned node embeddings which consider each node's representation as multiple independent scalar features.However,they neglect the detailed mutual relations among different node features such as position,direction,and connection.