This paper presents the Global and Local Confidence Graph Neural Network (GLC-GNN), an innovative approach to graph-based anomaly detection that addresses the challenges of heterophily and camouflage in fraudulent activities. By introducing a prototype to encapsulate the global features of a graph and calculating a Global Confidence (GC) value for each node, GLC-GNN effectively distinguishes between benign and fraudulent nodes. The model leverages GC to generate attention values for message aggregation, enhancing its ability to capture both homophily and heterophily. Through extensive experiments on four open datasets, GLC-GNN demonstrates superior performance over state-of-the-art models in accuracy and convergence speed, while maintaining a compact model size and expedited training process. The integration of global and local confidence measures in GLC-GNN offers a robust solution for detecting anomalies in graphs, with significant implications for fraud detection across diverse domains.

翻译：本文提出了一种基于全局与局部置信度的图神经网络（GLC-GNN），这是一种创新的基于图的异常检测方法，旨在解决欺诈活动中的异配性和伪装问题。通过引入原型来封装图的全局特征，并为每个节点计算全局置信度（GC）值，GLC-GNN能够有效区分良性节点与欺诈节点。该模型利用GC生成消息聚合的注意力值，从而增强其捕捉同配性与异配性的能力。通过在四个公开数据集上的大量实验，GLC-GNN在准确率和收敛速度方面均表现出优于现有先进模型的性能，同时保持了紧凑的模型规模和高效的训练过程。GLC-GNN中全局与局部置信度度量的结合为图中异常检测提供了稳健的解决方案，对跨多个领域的欺诈检测具有重要影响。