arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.06859cs.LGcs.AI
收藏

零射一般化图异常检测与混合黎曼专家

Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts

School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院);Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University(教育区块链与智能技术重点实验室,教育部,广西师范大学)

Xinyu Zhao, Qingyun Sun, Jiayi Luo, Xingcheng Fu, Jianxin Li

AI总结:

GAD-MoRE通过混合黎曼专家架构实现零射一般化图异常检测,利用多曲率空间建模提升异常检测能力。

摘要:

图异常检测(GAD)旨在识别图数据中的不规则模式,最近的研究探索了零射一般化GAD以实现对未见图数据集的泛化。然而,现有的零射GAD方法大多忽略了在不同异常模式之间固有的几何差异,大大限制了其跨领域泛化能力。在本工作中,我们揭示出异常检测能力高度依赖于底层的几何属性,并且将来自不同领域的图嵌入到单一静态曲率空间中会扭曲异常的结构特征。为了解决单一曲率空间无法捕捉几何依赖的图异常模式这一挑战,我们提出了GAD-MoRE,一种新的零射一般化图异常检测框架,采用混合黎曼专家架构。具体来说,为了确保每个异常模式在最能检测它的黎曼空间中被建模,GAD-MoRE使用一组专门的黎曼专家网络,每个网络在不同的曲率空间中运行。为了将原始节点特征与曲率特定的异常特征对齐,我们引入了一个异常感知的多曲率特征对齐模块,将输入投影到平行的黎曼空间中,从而捕捉多样的几何特征。最后,为了促进在未见模式上的更好泛化,我们设计了一个基于记忆的动态路由器,根据历史上在相似异常上的重建性能,自适应地将每个输入分配给最兼容的专家。在零射设置下的大量实验表明,GAD-MoRE显著优于最先进的通用GAD基线,并且甚至超过了通过目标领域标注数据进行少量细调的强竞争者。

英文摘要:

Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to enable generalization to unseen graph datasets. However, existing zero-shot GAD methods largely ignore intrinsic geometric differences across diverse anomaly patterns, substantially limiting their cross-domain generalization. In this work, we reveal that anomaly detectability is highly dependent on the underlying geometric properties and that embedding graphs from different domains into a single static curvature space can distort the structural signatures of anomalies. To address the challenge that a single curvature space cannot capture geometry-dependent graph anomaly patterns, we propose GAD-MoRE, a novel framework for zero-shot Generalizable Graph Anomaly Detection with a Mixture of Riemannian Experts architecture. Specifically, to ensure that each anomaly pattern is modeled in the Riemannian space where it is most detectable, GAD-MoRE employs a set of specialized Riemannian expert networks, each operating in a distinct curvature space. To construct topology-aware inputs for the subsequent Riemannian experts, we introduce an anomaly-aware multi-curvature feature alignment module that combines dimensionality reduction with Laplacian feature selection over parallel feature branches. Finally, to facilitate better generalization beyond seen patterns, we design a memory-based dynamic router that adaptively assigns each input to the most compatible expert based on historical reconstruction performance on similar anomalies. Extensive experiments in the zero-shot setting demonstrate that GAD-MoRE significantly outperforms state-of-the-art generalist GAD baselines.

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。

↑