通过对比学习与最优传输提升图节点聚类效果，解决传统方法的聚类混淆问题。
THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings
- 引入语义原型和跨视图预测任务，增强节点区分能力
- 利用融合式格罗莫夫-沃瑟斯坦传输挖掘图结构聚类信息
- 动量更新机制适应真实数据多样性，聚类分离性显著提升
图节点聚类是基础的无监督任务。现有方法通常通过自监督训练编码器，再对编码输出应用K-means进行聚类。部分方法直接使用该聚类结果，另一些则以初始聚类初始化可学习质心并联合微调编码器与质心。然而，由于依赖K-means，当编码器输出的聚类可分性较低时，易受均匀效应（Uniform Effect）和聚类同化（Cluster Assimilation）影响。我们总结三个导致聚类可分性低的原因：(1) 缺乏上下文信息，难以区分不同簇中相似节点；(2) 训练任务与下游聚类任务不匹配；(3) 未有效利用图结构中的聚类信息。为此，我们提出基于交换融合格罗莫夫-沃瑟斯坦耦合的对比图聚类方法（THESAURUS）。该方法引入语义原型提供上下文信息，设计与下游聚类任务高度对齐的跨视图分配预测预训练任务，并结合所提出的原型图，充分利用图结构中的聚类信息。为适应多样化现实数据，THESAURUS通过动量机制动态更新原型图与原型边际分布。大量实验表明，THESAURUS在聚类可分性上优于先前方法，有效缓解了均匀效应与聚类同化问题。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。