自监督对比属性图聚类
Self-supervised Contrastive Attributed Graph Clustering
AI总结：
提出自监督对比属性图聚类网络SCAGC，利用不精确聚类标签设计自监督对比损失学习节点表示，并直接输出聚类标签，解决样本外问题，在四个基准数据集上优于11种方法。
摘要：
属性图聚类通过从节点属性和拓扑图中学习节点表示来进行聚类，是图分析中一项基础但具有挑战性的任务。近年来，基于图对比学习（GCL）的方法在该任务上取得了令人瞩目的聚类性能。然而，我们观察到现有的基于GCL的方法存在以下问题：1）无法从不够精确的聚类标签中获益；2）需要后处理操作才能获得聚类标签；3）无法解决样本外（OOS）问题。为解决这些问题，我们提出了一种新颖的属性图聚类网络，即自监督对比属性图聚类（SCAGC）。在SCAGC中，通过利用不精确的聚类标签，设计了一种自监督对比损失用于节点表示学习，该损失旨在最大化簇内节点的相似性，同时最小化簇间节点的相似性。同时，构建了一个聚类模块，通过对比不同簇的表示来直接输出聚类标签。因此，对于OOS节点，SCAGC可以直接计算其聚类标签。在四个基准数据集上的大量实验结果表明，SCAGC始终优于11种具有竞争力的聚类方法。
英文摘要：
Attributed graph clustering, which learns node representation from node attribute and topological graph for clustering, is a fundamental but challenging task for graph analysis. Recently, methods based on graph contrastive learning (GCL) have obtained impressive clustering performance on this task. Yet, we observe that existing GCL-based methods 1) fail to benefit from imprecise clustering labels; 2) require a post-processing operation to get clustering labels; 3) cannot solve out-of-sample (OOS) problem. To address these issues, we propose a novel attributed graph clustering network, namely Self-supervised Contrastive Attributed Graph Clustering (SCAGC). In SCAGC, by leveraging inaccurate clustering labels, a self-supervised contrastive loss, which aims to maximize the similarities of intra-cluster nodes while minimizing the similarities of inter-cluster nodes, are designed for node representation learning. Meanwhile, a clustering module is built to directly output clustering labels by contrasting the representation of different clusters. Thus, for the OOS nodes, SCAGC can directly calculate their clustering labels. Extensive experimental results on four benchmark datasets have shown that SCAGC consistently outperforms 11 competitive clustering methods.
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。
