arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.14930cs.LGcs.AIcs.SI
收藏

基于图神经网络的图异常检测:现状与挑战

Graph Anomaly Detection with Graph Neural Networks: Current Status and Challenges

Chungnam National University(忠南国立大学);University of Vermont(佛蒙特大学);Yonsei University(延世大学);Pohang University of Science and Technology(浦项科技大学)

Hwan Kim, Byung Suk Lee, Won-Yong Shin, Sungsu Lim

摘要:

图被广泛地用于复杂系统的建模,而图中的异常检测是复杂系统分析中的一项重要任务。图异常是图中不符合图的属性和/或结构所期望的正常模式的模式。近年来,图神经网络(GNN)已经被广泛研究,并且由于经由有效学习图表示的消息传递的高度表达能力,已经成功地在节点分类、链接预测和图分类中执行困难的机器学习任务。为了解决图异常检测问题,基于GNN的方法利用关于图属性(或特征)和/或结构的信息来学习适当地对异常进行评分。在这项调查中,我们回顾了最近的进展,在检测图异常使用GNN模型。具体来说,我们根据图类型(即,静态和动态),异常类型(即,节点、边、子图和整个图),以及网络体系结构(例如,图自动编码器、图卷积网络)。据我们所知,这项调查是第一次全面审查基于GNNs的图异常检测方法。

英文摘要:

Graphs are used widely to model complex systems, and detecting anomalies in a graph is an important task in the analysis of complex systems. Graph anomalies are patterns in a graph that do not conform to normal patterns expected of the attributes and/or structures of the graph. In recent years, graph neural networks (GNNs) have been studied extensively and have successfully performed difficult machine learning tasks in node classification, link prediction, and graph classification thanks to the highly expressive capability via message passing in effectively learning graph representations. To solve the graph anomaly detection problem, GNN-based methods leverage information about the graph attributes (or features) and/or structures to learn to score anomalies appropriately. In this survey, we review the recent advances made in detecting graph anomalies using GNN models. Specifically, we summarize GNN-based methods according to the graph type (i.e., static and dynamic), the anomaly type (i.e., node, edge, subgraph, and whole graph), and the network architecture (e.g., graph autoencoder, graph convolutional network). To the best of our knowledge, this survey is the first comprehensive review of graph anomaly detection methods based on GNNs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑