检索结果-内蒙古大学图书馆

Frequency Self-Adaptation graph Neural Network for unsupervised graph anomaly detection

Neural networks : the official journal of the International Neural Network Society 2025年 190卷 107612页

作者： Ming Gu Gaoming Yang Zhuonan Zheng Meihan Liu Haishuai Wang Jiawei Chen Sheng Zhou Jiajun Bu College of Computer Science and Technology Zhejiang University Hangzhou 310027 China. Electronic address: guming444@***. Taobao and Tmall Group Hangzhou 310052 China. Electronic address: yanggaoming.ygm@***. College of Computer Science and Technology Zhejiang University Hangzhou 310027 China. Electronic address: zhengzn@***. College of Computer Science and Technology Zhejiang University Hangzhou 310027 China. Electronic address: lmh_zju@***. College of Computer Science and Technology Zhejiang University Hangzhou 310027 China Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems Zhejiang University Hangzhou 310027 China. Electronic address: haishuai.wang@***. College of Computer Science and Technology Zhejiang University Hangzhou 310027 China. Electronic address: sleepyhunt@***. Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems Zhejiang University Hangzhou 310027 China School of Software Technology Zhejiang University Ningbo 315048 China. Electronic address: zhousheng_zju@***. Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems Zhejiang University Hangzhou 310027 China. Electronic address: bjj@***.

unsupervised graph anomaly detection (UGAD) seeks to identify abnormal patterns in graphs without relying on labeled data. Among existing UGAD methods, graph Neural Networks (GNNs) have played a critical role in learning effective representation for detection by filtering low-frequency graph signals. However, the presence of anomalies can shift the frequency band of graph signals toward higher frequencies, thereby violating the fundamental assumptions underlying GNNs and anomaly detection frameworks. To address this challenge, the design of novel graph filters has garnered significant attention, with recent approaches leveraging anomaly labels in a semi-supervised manner. Nonetheless, the absence of anomaly labels in real-world scenarios has rendered these methods impractical, leaving the question of how to design effective filters in an unsupervised manner largely unexplored. To bridge this gap, we propose a novel Frequency Self-Adaptation graph Neural Network for unsupervised graph anomaly detection (FAGAD). Specifically, FAGAD adaptively fuses signals across multiple frequency bands using full-pass signals as a reference. It is optimized via a self-supervised learning approach, enabling the generation of effective representations for unsupervised graph anomaly detection. Experimental results demonstrate that FAGAD achieves state-of-the-art performance on both artificially injected datasets and real-world datasets. The code and datasets are publicly available at https://***/eaglelab-zju/FAGAD.

关键词： graph Neural Networks graph filtering unsupervised graph anomaly detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：