基于噪声过滤与特征增强的图神经网络欺诈检测方法OACSCDCSTPCD
Noise Filtering and Feature Enhancement Based Graph Neural Network Method for Fraud Detection
现有的基于图神经网络(Graph Neural Network,GNN)的欺诈检测方法还存在三个方面的不足:(1)没有充分考虑到样本标签分布不平衡的问题;(2)没有考虑欺诈者为了躲避检测器的检测,故意制造噪声干扰检测的问题;(3)没有考虑欺诈类型数据联系稀疏问题.为此,本文提出一种基于噪声过滤与特征增强的图神经网络欺诈检测方法NFE-GNN(Noise Filtering and feature Enhancement based Graph N…查看全部>>
Existing graph neural network(GNN)-based fraud detection methods have at least three shortcomings:(1)They do not adequately consider the problem of imbalanced distribution of sample labels.(2)They do not take into ac-count the problem that fraudsters deliberately create noise to interfere with fraud detection in order to avoid detection by de-tectors.(3)They fail to consider the limitations of sparse connections for fraud data.To address these three shortcom…查看全部>>
李康和;黄震华
华南师范大学人工智能学院,广东佛山 528225华南师范大学人工智能学院,广东佛山 528225||华南师范大学计算机学院,广东广州 510631
计算机与自动化
欺诈检测类不平衡节点分类图结构数据图神经网络性能评估
fraud detectionclass imbalancenode classificationgraph datagraph neural networkperformance evaluation
《电子学报》 2023 (11)
基于深度表示—度量学习的推荐方法关键问题研究
3053-3060,8
国家自然科学基金(No.62172166)广东省基础与应用基础研究基金(No.2022A1515011380)National Natural Science Foundation of China(No.62172166)Guangdong Basic and Applied Basic Research Foundation(No.2022A1515011380)
评论