Deep Masked Graph Node Clustering

In recent years, reconstructing features and learning node representations by graph autoencoders (GAE) have attracted much attention in deep graph node clustering. However, existing works often overemphasize structural information and overlook the impact of real-world prevalent noise on feature learning and clustering with graph data, which may be detrimental to robust training. To address these issues, the utilization of a masking strategy that specifically focuses on feature reconstruction may mitigate these limitations. In this article, we propose a graph node clustering generative method named deep masked graph node clustering (DMGNC), which leverages a masked autoencoder to effectively reconstruct node features, enabling the discovery of latent information crucial for accurate node clustering. Additionally, a clustering self-optimization module is designed to guide the iterative update of our end-to-end clustering framework. Further, we extend the masked graph autoencoder (MGA) and develop a contrastive method called deep masked graph node contrastive clustering (DMGNCC), which applies the MGA to graph node contrastive learning at both the node level and the class level in a united model. Extensive experimental results on real-world graph benchmark datasets demonstrate the effectiveness and superiority of the proposed method.