arXiv 2507.190952025-07-31cs.LG

GCL-GCN：Graphormer与对比学习增强的属性图聚类网络

GCL-GCN: Graphormer and Contrastive Learning Enhanced Attributed Graph Clustering Network

Stirling College, Chengdu University（成都大学斯特林学院）；Chengdu University（成都大学）

Binxiong Li, Xu Xiang, Xue Li, Quanzhou Lou, Binyu Zhao, Yujie Liu, Huijie Tang, Benhan Yang

备注：: The source code for this study is available at https://github.com/YF-W/GCL-GCN

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对属性图聚类中稀疏异构图数据处理的局部依赖与复杂结构捕获难题，提出融合Graphormer模块与对比学习模块的GCL-GCN模型，在六个数据集上聚类效果优于14种先进方法。

摘要：

属性图聚类在现代数据分析中具有重要意义。然而，由于图数据的复杂性和节点属性的异质性，利用图信息进行聚类仍具挑战性。为解决这一问题，我们提出一种新型深度图聚类模型GCL-GCN，专门用于应对现有模型在处理稀疏异构图数据时，在捕获局部依赖关系和复杂结构方面存在的局限。GCL-GCN引入了创新的Graphormer模块，该模块结合中心性编码与空间关系，能够有效捕获节点间的全局与局部信息，从而提升节点表示的质量。此外，我们提出了一种新型对比学习模块，可显著增强特征表示的判别能力。在预训练阶段，该模块通过对原始特征矩阵进行对比学习来增大特征区分度，为后续的图卷积和聚类任务提供更具可识别性的初始表示。在六个数据集上开展的大量实验结果表明，GCL-GCN在聚类质量和鲁棒性方面优于14种先进方法。具体而言，在Cora数据集上，与主要对比方法MBN相比，其ACC、NMI和ARI分别提升了4.94%、13.01%和10.97%。

英文摘要：

Attributed graph clustering holds significant importance in modern data analysis. However, due to the complexity of graph data and the heterogeneity of node attributes, leveraging graph information for clustering remains challenging. To address this, we propose a novel deep graph clustering model, GCL-GCN, specifically designed to address the limitations of existing models in capturing local dependencies and complex structures when dealing with sparse and heterogeneous graph data. GCL-GCN introduces an innovative Graphormer module that combines centrality encoding and spatial relationships, effectively capturing both global and local information between nodes, thereby enhancing the quality of node representations. Additionally, we propose a novel contrastive learning module that significantly enhances the discriminative power of feature representations. In the pre-training phase, this module increases feature distinction through contrastive learning on the original feature matrix, ensuring more identifiable initial representations for subsequent graph convolution and clustering tasks. Extensive experimental results on six datasets demonstrate that GCL-GCN outperforms 14 advanced methods in terms of clustering quality and robustness. Specifically, on the Cora dataset, it improves ACC, NMI, and ARI by 4.94%, 13.01%, and 10.97%, respectively, compared to the primary comparison method MBN.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。