Self-supervised graph autoencoder with redundancy reduction for community detection

• Published in: Neurocomputing (Amsterdam) 2024-07, Vol.590, p.127703, Article 127703
• Main Authors: Wang, Xiaofeng, Shen, Guodong, Zhang, Zengjie, Lai, Shuaiming, Zhu, Shuailei, Chen, Yuntao, Quan, Daying
• Format: Article
• Language: English
• Subjects: Community detection; Graph autoencoder; Multi-scale features; Redundancy reduction; Self-supervised learning
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2024.127703

Community detection is a significant research topic in network science, which has been revisited with graph neural networks. As a powerful graph representation learning model, graph autoencoder (GAE) is commonly used for unsupervised community detection. However, most GAE-based methods ignore multi-scale features of encoding layers, which inherently provide useful information for community detection. Moreover, these methods fail to simultaneously improve the representation learning process and clustering performance through a unified objective function. To address these issues, we propose a self-supervised graph autoencoder model with redundancy reduction for community detection. Firstly, we introduce a multi-scale module based on GAE to obtain discriminative node representations from different encoding layers. In particular, a redundancy reduction strategy is employed to eliminate redundancy information in the latent embedding space. Then, a node clustering module is used to obtain initial community labels. To fully utilize the multi-scale features to further refine clustering performance, a self-supervised module is designed to utilize current clustering labels to supervise the node representation learning process, thus constructing an end-to-end model for community detection. Finally, we validate the effectiveness of the proposed method on real-world networks. Experimental results demonstrate that our method outperforms several state-of-the-art methods in community detection.