发表机构
School of Computer Science and Technology, East China Normal University; State Key Laboratory of Submarine Geoscience, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（华东师范大学计算机科学与技术学院; 上海交通大学海洋地质国家重点实验室、自动化与智能传感学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有图异常检测方法依赖同质性假设、鲁棒性不足的问题，提出RagGAD框架，通过依据解缠与混合建模提升性能，在多基准数据集上优于现有方法。
AI 中文摘要
图异常检测旨在识别图中偏离正常行为模式的节点。然而，现有方法大多依赖同质性假设，这使得它们难以区分虚假关联，也难以捕捉正常节点的多样化行为，从而限制了其在复杂真实场景中的鲁棒性。为解决该问题，我们提出了RagGAD，一种基于依据感知条件高斯混合归一化流的无监督图异常检测框架。RagGAD引入自适应依据解缠器，从节点相互关系中解缠出稳定依据与虚假关联，并进一步将稳定依据分解为稳健和脆弱成分。学习到的依据能捕捉不同条件下表征正常行为的潜在交互模式，而异常则表现为与不稳定或虚假关联相关的偏差。为建模正常节点与异常节点的复杂分布，RagGAD整合了依据-非依据高斯混合建模与稳健-脆弱依据混合学习策略。通过缓解虚假同质性关联并接纳正常模式的异质性，RagGAD将异常识别为结构感知分布空间中的低密度区域。在多个基准数据集上的大量实验表明，RagGAD的性能优于当前最先进的方法。
英文摘要
Graph anomaly detection aims to identify nodes that deviate from normal behavioral patterns within graphs. However, existing methods largely rely on the homophily assumption, which makes it difficult to distinguish spurious affinities and to capture the diverse behaviors of normal nodes,limiting their robustness in complex real-world scenarios. To address this problem, we propose RagGAD, an unsupervised graph anomaly detection framework based on rationale-aware conditional Gaussian mixture normalizing flow. RagGAD introduces an adaptive rationale disentangler to disentangle stable rationales from spurious correlations within node interrelationships, and further decomposes stable rationales into robust and fragile components. The learned rationales capture underlying interaction patterns that characterize normal behaviors under varying conditions, while anomalies emerge as deviations associated with unstable or spurious correlations. To model the intricate distributions of normal and abnormal nodes, RagGAD integrates rationale-non-rationale Gaussian mixture modeling with a robust-fragile rationale mixture learning strategy. By mitigating spurious homophilic correlations and embracing the heterogeneity of normal patterns, RagGAD identifies anomalies as low-density regions within a structure-aware distribution space. Extensive experiments on multiple benchmark datasets demonstrate that RagGAD outperforms state-of-the-art methods.
