多模态属性图的跨对比聚类：带有双图过滤的多视图图聚类
Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering
AI总结：
本文提出双图过滤方案，通过特征去噪和三交叉对比学习提升多模态属性图的聚类性能。
摘要：
多模态属性图（MMAGs）是一种表达复杂实体间相互关联的表达数据模型，这些实体关联了来自多种数据模态（如文本、图像等）的属性。在这样的数据上进行聚类发现了许多在现实场景中的实际应用，包括社交社区检测、医疗数据分析等。然而，正如我们的实证研究所揭示的，现有的多视图聚类解决方案大多依赖于不同视图之间属性的高相关性，并忽略了多模态属性输出由大型预训练语言和视觉模型产生的独特特征（例如，低模态间相关性和强烈特征间噪声），导致聚类性能不理想。受前述实证观察和图信号处理的理论分析启发，我们提出了双图过滤（DGF）方案，该方案创新性地将特征级去噪组件纳入节点表示学习中，从而有效克服了传统图滤波器在现有多视图图聚类方法中的局限性。此外，DGF还包括一个三交叉对比训练策略，该策略通过实例级跨模态、邻域和社区的对比学习来学习稳健且判别性的节点表示。我们在八个基准MMAG数据集上的综合实验表明，DGF在聚类质量方面能够显著优于一系列最先进的基线方法。
英文摘要：
Multimodal Attributed Graphs (MMAGs) are an expressive data model for representing the complex interconnections among entities that associate attributes from multiple data modalities (text, images, etc.). Clustering over such data finds numerous practical applications in real scenarios, including social community detection, medical data analytics, etc. However, as revealed by our empirical studies, existing multi-view clustering solutions largely rely on the high correlation between attributes across various views and overlook the unique characteristics (e.g., low modality-wise correlation and intense feature-wise noise) of multimodal attributes output by large pre-trained language and vision models in MMAGs, leading to suboptimal clustering performance. Inspired by foregoing empirical observations and our theoretical analyses with graph signal processing, we propose the Dual Graph Filtering (DGF) scheme, which innovatively incorporates a feature-wise denoising component into node representation learning, thereby effectively overcoming the limitations of traditional graph filters adopted in the extant multi-view graph clustering approaches. On top of that, DGF includes a tri-cross contrastive training strategy that employs instance-level contrastive learning across modalities, neighborhoods, and communities for learning robust and discriminative node representations. Our comprehensive experiments on eight benchmark MMAG datasets exhibit that DGF is able to outperform a wide range of state-of-the-art baselines consistently and significantly in terms of clustering quality measured against ground-truth labels.
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。
