用欧氏与双曲空间联合建模，更精准发现图中异常节点。
Combining Euclidean and Hyperbolic Representations for Node-level Anomaly Detection
- 双视角融合：原始特征+结构特征，分别映射到欧氏与双曲空间。
- 对比学习对齐两空间表示，不一致节点即为潜在异常。
- 在4个真实数据集上超越主流方法，适合复杂异常检测场景。
节点级异常检测因结构模式多样、特征分布复杂而极具挑战，广泛应用于欺诈识别、网络安全和推荐系统等领域。本文提出Janus框架，联合使用欧氏与双曲图神经网络，捕捉节点表示的互补特性。每个节点通过原始特征及基于随机游走和度数提取的结构特征构成双重视图，分别嵌入欧氏空间与双曲空间。采用多图自编码器架构，并引入对比学习作为正则项，对齐两空间中的嵌入表示，使难以匹配的节点视图被突出，从而判定为异常。在四个真实世界数据集上的实验表明，Janus持续优于浅层与深层基线模型，实证证明结合多种几何表示能有效识别图中细微且复杂的异常。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。