THESAURUS：通过交换融合的 Gromov-Wasserstein 耦合实现对比图聚类
THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings
AI总结：
针对自监督图聚类依赖 K-means 导致簇可分性低的问题，提出 THESAURUS，用语义原型、跨视图预测和动量更新的 GW-OT 原型图提升聚类性能。
摘要：
图节点聚类是一项基础的无监督任务。现有方法通常通过自监督学习训练编码器，然后对编码器输出应用 K-means。一些方法直接将该聚类结果用作最终分配，而另一些方法则基于这一初始聚类初始化质心，随后对编码器和这些可学习质心进行微调。然而，由于依赖 K-means，当编码器输出的簇可分性较低时，这些方法会继承其缺陷，面临 Uniform Effect（均匀效应）和 Cluster Assimilation（簇同化）带来的挑战。我们总结了现有方法中簇可分性较低的三个原因：（1）缺乏上下文信息，导致无法区分来自不同簇的相似节点；（2）训练任务与下游聚类任务没有充分对齐；（3）图结构中的簇信息没有得到适当利用。为解决这些问题，我们提出了通过交换融合的 Gromov-Wasserstein 耦合实现对比图聚类的方法 THESAURUS。该方法引入语义原型以提供上下文信息，并采用与下游聚类任务良好对齐的跨视图分配预测预文本任务。此外，它利用 Gromov-Wasserstein 最优传输（GW-OT）以及所提出的原型图，充分挖掘图结构中的簇信息。为适应多样化的真实世界数据，THESAURUS 使用动量更新 OT 中的原型图和原型边缘分布。大量实验表明，THESAURUS 相比现有技术实现了更高的簇可分性，有效缓解了 Uniform Effect 和 Cluster Assimilation 问题。
英文摘要：
Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through selfsupervised learning and then apply K-means to the encoder output. Some methods use this clustering result directly as the final assignment, while others initialize centroids based on this initial clustering and then finetune both the encoder and these learnable centroids. However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation. We summarize three reasons for the low cluster separability in existing methods: (1) lack of contextual information prevents discrimination between similar nodes from different clusters; (2) training tasks are not sufficiently aligned with the downstream clustering task; (3) the cluster information in the graph structure is not appropriately exploited. To address these issues, we propose conTrastive grapH clustEring by SwApping fUsed gRomov-wasserstein coUplingS (THESAURUS). Our method introduces semantic prototypes to provide contextual information, and employs a cross-view assignment prediction pretext task that aligns well with the downstream clustering task. Additionally, it utilizes Gromov-Wasserstein Optimal Transport (GW-OT) along with the proposed prototype graph to thoroughly exploit cluster information in the graph structure. To adapt to diverse real-world data, THESAURUS updates the prototype graph and the prototype marginal distribution in OT by using momentum. Extensive experiments demonstrate that THESAURUS achieves higher cluster separability than the prior art, effectively mitigating the Uniform Effect and Cluster Assimilation issues
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。
