Affiliations: [a] College of Computer and Information Engineering, Xiamen University of Technology, Jimei District, Xiamen, China | [b] Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Jimei District, Xiamen, China | [c] Xiamen Fuyun Information Tech. Co., Siming District, Xiamen, China
Correspondence:
[*]
Corresponding author: Wei Weng, College of Computer and Information Engineering, Xiamen University of Technology, Jimei District, No.600 Ligong Road, Xiamen 361024, China. E-mail: [email protected].
Note: [1] Wei Weng and Fengxia Hou contributed equally to this work.
Abstract: Graph clustering is a crucial technique for partitioning graph data. Recent research has concentrated on integrating topology and attribute information from attribute graphs to generate node embeddings, which are subsequently clustered using classical algorithms. However, these methods have some limitations, such as insufficient information inheritance in shallow networks or inadequate quality of reconstructed nodes, leading to suboptimal clustering performance. To tackle these challenges, we introduce two normalization techniques within the graph attention autoencoder framework, coupled with an MSE loss, to facilitate node embedding learning. Furthermore, we integrate Transformers into the self-optimization module to refine node embeddings and clustering outcomes. Our model can induce appropriate node embeddings for graph clustering in a shallow network. Our experimental results demonstrate that our proposed approach outperforms the state-of-the-art in graph clustering over multiple benchmark datasets. In particular, we achieved 76.3% accuracy on the Pubmed dataset, an improvement of at least 7% compared to other methods.
