DDGAD：基于扩散的图异常检测中的轨迹动力学
DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine
AI总结：
提出DDGAD框架，利用扩散正则化和可靠性感知邻域共识下的轨迹动力学区分正常与异常节点，通过三种互补异常信号检测异常。
摘要：
图异常检测（GAD）旨在识别图结构数据中行为或属性显著偏离整体模式的节点或子结构，在金融风险控制、社交网络分析和网络安全等领域具有关键应用。然而，现有的基于GCN的方法存在污染传播的根本问题，即异常节点通过消息传递污染其邻居的表示，导致检测性能下降。本文提出DDGAD，一种新颖的基于扩散的图异常检测框架，利用轨迹动力学区分正常和异常节点。我们的关键洞察是，在扩散正则化和可靠性感知邻域共识的耦合作用下，正常节点表现出一致且稳定的表示轨迹，而异常节点由于全局流形先验与局部污染消息传递之间的方向不一致，表现出不稳定且冲突的动力学。为了减轻污染传播，我们引入了一种分布式的可靠性感知共识细化机制，并定义了三种互补的异常信号：邻居不一致性、可靠性权重和动力学冲突能量。我们进一步对耦合动力学下的正常节点稳定性进行了初步的理论分析。这些信号从局部不一致性、共识可靠性和动力学不稳定性角度共同刻画异常行为。在五个真实世界数据集上的大量实验证明了所提框架的有效性。
英文摘要：
Graph anomaly detection (GAD) commonly relies on message passing to jointly encode node attributes and neighborhood context. However, once the two are mixed, an abnormal post-encoding state may reflect either an intrinsic node deviation or incompatible contextual influence, making its source ambiguous. We propose Disagreement-Driven Graph Anomaly Detection (DDGAD), which treats persistent incompatibility between node-wise and contextual estimates as anomaly evidence. Inspired by Adapt-Then-Combine (ATC), DDGAD reverses its consensus objective: Adapt produces a node-wise estimate without new same-step neighbor aggregation, while Combine forms a neighborhood-dependent contextual estimate, and their pre-consensus disagreement is accumulated across ATC steps for detection. We further characterize this signal from graph-spectral and source-response perspectives and derive sufficient conditions for anomaly--normal separation under contextual mixing. Experiments on six benchmarks show the highest average AUROC among the evaluated methods, while controlled interventions and Adapt-operator controls further support persistent disagreement as an effective detection signal.
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。
