注意力增强和深度可分离的卷积信息在大型图表中传递强大的欺诈检测
Ijeoma A Chikwendu1, Xiaoling Zhang1, Chiagoziem C Ukwuoma2
1School of Information and Communication Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China.
Journal of advanced research
|July 1, 2025
概括
本研究介绍了注意力增强和深度可分离的卷积信息传递 (ADSCMP),这是一种用于增强欺诈检测的新型图形神经网络 (GNN). 在复杂的图表中,ADSCMP通过从同性恋和异性恋邻居中学习,有效地识别欺诈活动.
科学领域:
- 图形神经网络的神经网络
- 机器学习 机器学习
- 欺诈检测 欺诈检测 欺诈检测
背景情况:
- 图形神经网络 (GNN) 显示出对欺诈检测的承诺,但与标签不平衡和异性邻居作斗争.
- 现有的GNN经常修改图形结构,忽略异性恋连接,这限制了现实世界的欺诈检测.
- 解决这些局限性对于改善大规模图形欺诈的检测至关重要.
研究的目的:
- 提出一个新的GNN框架,注意力增强和深度可分离的卷积信息传递 (ADSCMP).
- 提高复杂的,现实世界的图表上的欺诈检测准确性和可扩展性.
- 通过有效处理同型和异型邻居来提高GNN的性能.
主要方法:
- 在消息传递过程中,ADSCMP将邻居分为同性恋,异性恋和未知群体.
- 采用轻量级的注意力机制和深度可分离的卷曲以提高效率.
- 动态生成根特异性重量矩阵,并集成光谱和空间特征.
主要成果:
- 在监督环境中,在基准数据集上获得高AUC分数 (例如,亚马逊的97.91%,YelpChi的94.17%).
- 保持强的表现 (例如,亚马逊的93.15%,YelpChi的84.53%) 即使在半监督的设置中使用1%的标记数据.
- 与基线相比,演示了较短的推断时间,适合实时应用.
结论:
- ADSCMP通过从不同的邻居类型中学习来提高欺诈检测的准确性和可扩展性.
- 该框架的高效信息传递和注意力机制提高了复杂图表的性能.
- ADSCMP提供了一个强大的解决方案,用于在大型图形数据中实时检测欺诈行为.
相关概念视频
Uniform Depth Channel Flow: Problem Solving
131
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
131
Convolution: Math, Graphics, and Discrete Signals
432
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
432

