基于多尺度加权成对粗化与对比学习的属性图聚类
Attributed Graph Clustering with Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning
AI总结：
提出 MPCCL 属性图聚类模型，利用多尺度加权成对粗化保留结构，并通过一对多对比、图重建与 KL 约束提升特征多样性和跨尺度一致性。
摘要：
本研究提出了 Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning（MPCCL，基于多尺度权重的成对粗化与对比学习）模型，这是一种用于属性图聚类的新颖方法，有效弥合了现有方法中的关键缺陷，包括长程依赖、特征坍缩和信息丢失。传统方法由于依赖低阶属性信息，往往难以捕获高阶图特征；而对比学习技术因过度强调局部邻域结构，在特征多样性方面存在局限。同样，传统图粗化方法虽然能够缩小图规模，却经常丢失细粒度结构细节。MPCCL 通过创新的多尺度粗化策略应对这些挑战：该策略逐步压缩图，并基于全局节点相似性优先合并关键边，以保留必要的结构信息。它还引入了一对多对比学习范式，将节点嵌入与增强图视图和聚类质心相结合，以增强特征多样性，同时缓解多尺度粗化过程中高频节点权重累积所导致的特征掩蔽问题。通过在其自监督学习框架中纳入图重建损失和 KL 散度，MPCCL 确保了节点表示的跨尺度一致性。实验评估表明，MPCCL 在聚类性能上取得显著提升，包括在 ACM 数据集上 NMI 显著提高 15.24%，并在 Citeseer、Cora 和 DBLP 等较小规模数据集上取得明显且稳健的增益。
英文摘要：
This study introduces the Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning (MPCCL) model, a novel approach for attributed graph clustering that effectively bridges critical gaps in existing methods, including long-range dependency, feature collapse, and information loss. Traditional methods often struggle to capture high-order graph features due to their reliance on low-order attribute information, while contrastive learning techniques face limitations in feature diversity by overemphasizing local neighborhood structures. Similarly, conventional graph coarsening methods, though reducing graph scale, frequently lose fine-grained structural details. MPCCL addresses these challenges through an innovative multi-scale coarsening strategy, which progressively condenses the graph while prioritizing the merging of key edges based on global node similarity to preserve essential structural information. It further introduces a one-to-many contrastive learning paradigm, integrating node embeddings with augmented graph views and cluster centroids to enhance feature diversity, while mitigating feature masking issues caused by the accumulation of high-frequency node weights during multi-scale coarsening. By incorporating a graph reconstruction loss and KL divergence into its self-supervised learning framework, MPCCL ensures cross-scale consistency of node representations. Experimental evaluations reveal that MPCCL achieves a significant improvement in clustering performance, including a remarkable 15.24% increase in NMI on the ACM dataset and notable robust gains on smaller-scale datasets such as Citeseer, Cora and DBLP.
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。
