DEDGCN: Dual Evolving Dynamic Graph Convolutional Network

<div>The framework of DEDGCN. DEDGCN consists of two parts: the upper Node Evolution learning the stability characteristics of nodes and the lower GCN evolution learning dynamic structure characteristics of graphs. They work together to modify GCN and build an unsupervised graph convolutional network framework.</div>

Security and Communication Networks

fig1

Figure 1

Figure 1: DEDGCN: Dual Evolving Dynamic Graph Convolutional Network 