arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.13872cs.LG
收藏

用于多变量时间序列异常检测的边条件节点更新图神经网络

Edge Conditional Node Update Graph Neural Network for Multi-variate Time Series Anomaly Detection

Korea University(高丽大学)

Hayoung Jo, Seong-Whan Lee

AI总结:

针对多变量时间序列异常检测中图方法源节点表示缺乏边条件适应性的问题,提出 ECNU-GNN,通过边条件节点更新动态变换源节点表示,并在 SWaT、WADI、PSM 上显著提升 F1。

摘要:

随着信息物理系统的快速发展,传感器数量不断增加,使系统状态的人工监测显著复杂化。因此,基于图的时间序列异常检测方法因其能够显式表示传感器之间的关系而受到关注。然而,即使在更新不同的目标节点表示时,这些方法也通常在所有相连目标节点上应用统一的源节点表示。此外,常用于推断未知图结构的图注意力机制可能会限制源节点表示的多样性。本文提出边条件节点更新图神经网络(Edge Conditional Node-update Graph Neural Network,ECNU-GNN)。该模型配备边条件节点更新模块,可根据相连边动态变换源节点表示,以恰当地表示目标节点。我们在三个真实世界数据集 SWaT、WADI 和 PSM 上验证了性能。与 F1 最优基线模型相比,该模型的性能分别高出 5.4%、12.4% 和 6.0%。

英文摘要:

With the rapid advancement in cyber-physical systems, the increasing number of sensors has significantly complicated manual monitoring of system states. Consequently, graph-based time-series anomaly detection methods have gained attention due to their ability to explicitly represent relationships between sensors. However, these methods often apply a uniform source node representation across all connected target nodes, even when updating different target node representations. Moreover, the graph attention mechanism, commonly used to infer unknown graph structures, could constrain the diversity of source node representations. In this paper, we introduce the Edge Conditional Node-update Graph Neural Network (ECNU-GNN). Our model, equipped with an edge conditional node update module, dynamically transforms source node representations based on connected edges to represent target nodes aptly. We validate performance on three real-world datasets: SWaT, WADI, and PSM. Our model demonstrates 5.4%, 12.4%, and 6.0% higher performance, respectively, compared to best F1 baseline models.

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。

↑