结合欧几里得与双曲表示进行节点级异常检测
Combining Euclidean and Hyperbolic Representations for Node-level Anomaly Detection
AI总结：
提出Janus框架，联合欧几里得与双曲图神经网络捕捉节点互补表示，通过多图自编码器与对比学习对齐嵌入，突出异常节点，在四个数据集上优于基线。
摘要：
节点级异常检测（NAD）因结构模式多样和特征分布复杂而具有挑战性。因此，NAD 是一项关键任务，其应用范围涵盖欺诈检测、网络安全乃至推荐系统。我们提出了 Janus 框架，该框架联合利用欧几里得与双曲图神经网络来捕捉节点表示的互补方面。每个节点由两个视图描述，这两个视图由原始特征以及从随机游走和度数导出的结构特征组成，然后嵌入到欧几里得空间和双曲空间中。一个配备对比学习目标作为正则化项的多图自编码器框架，在欧几里得空间与双曲空间之间对齐嵌入，突出那些视图难以调和因而可能异常的节点。在四个真实世界数据集上的实验表明，Janus 始终优于浅层和深层基线，实证表明结合多种几何表示为识别图中细微而复杂的异常提供了一种稳健且有效的方法。
英文摘要：
Node-level anomaly detection (NAD) is challenging due to diverse structural patterns and feature distributions. As such, NAD is a critical task with several applications which range from fraud detection, cybersecurity, to recommendation systems. We introduce Janus, a framework that jointly leverages Euclidean and Hyperbolic Graph Neural Networks to capture complementary aspects of node representations. Each node is described by two views, composed by the original features and structural features derived from random walks and degrees, then embedded into Euclidean and Hyperbolic spaces. A multi Graph-Autoencoder framework, equipped with a contrastive learning objective as regularization term, aligns the embeddings across the Euclidean and Hyperbolic spaces, highlighting nodes whose views are difficult to reconcile and are thus likely anomalous. Experiments on four real-world datasets show that Janus consistently outperforms shallow and deep baselines, empirically demonstrating that combining multiple geometric representations provides a robust and effective approach for identifying subtle and complex anomalies in graphs.
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。
