Graph convolutional network reconstruction with high-order node information for community detection

Community detection is typically used to understand the community structures within networks. Most community detection methods are limited to capturing only the nodes’ first-order and second-order neighbor information. To utilize nodes’ high-order neighbor information, we propose a graph convolutional network reconstruction with high-order node information for community detection (GCNRH). Since the existing shallow graph convolutional network is difficult to capture high-order information, the GCNRH model introduces a graph convolutional network with a biaffine attention mechanism to establish a fast association of remote nodes. It utilizes the biaffine attention mechanism to capture the higher-order node information and learns the potential representation of nodes by reconstructing the modularity matrix. It also adopts a self-supervised training method to optimize the learning process. Extensive experiments on 12 real-world datasets demonstrate the superior performance of GCNRH in community detection. In particular, the modularity and normalized mutual information values of the GCNRH model improve by 0. 48%–30. 92% and 3. 8%–19. 3% on the Facebook dataset, respectively. Finally, visualizations of community divisions on different-scale networks show the effectiveness of the GCNRH model.

Authors

• Yukun Wang
• XianYong Li
• YaJun Du
• Dong Huang Carnegie Mellon University
• XiaoLiang Chen
• Zhicheng Dong
• Yujie Zhang

Keywords

• Community detection
• Graph convolutional network reconstruction
• Biaffine attention
• High-order relationships