用超图建模多变量时间序列高阶关联，提升异常检测精度。
Hypergraph-based multi-scale spatio-temporal graph convolution network for Time-Series anomaly detection
- 基于超图动态构建多变量间高阶依赖关系
- 融合多尺度膨胀卷积捕捉时序多粒度特征
- 无监督检测框架，适合标签稀缺场景
多变量时间序列异常检测在航空航天、污水处理、云服务等领域至关重要。随着数据规模与复杂度上升，且异常样本缺乏标注，实现高效准确的检测愈发困难。本文提出一种基于超图的时空图卷积网络模型 STGCN_Hyper，通过超图动态图结构学习模块显式捕捉多变量间的高阶、多跳关联。在此基础上，利用超图时空图卷积网络有效传播与聚合一跳及多跳节点信息，获得丰富的空间特征。同时，通过多尺度膨胀卷积模块（TCN）捕捉时间维度上不同尺度的特征依赖。模型还集成了基于PCA与GMM的无监督异常检测器，通过异常得分实现无监督异常识别。在多个时间序列数据集上的实验表明，该模型能灵活学习多尺度时序特征及变量间依赖关系，在精度、召回率、F1分数等指标上优于多数现有基线模型。代码已公开：https://git.ecdf.ed.ac.uk/msc-23-24/s2044819
原文摘要 · Abstract (English)
Multivariate time series anomaly detection technology plays an important role in many fields including aerospace, water treatment, cloud service providers, etc. Excellent anomaly detection models can greatly improve work efficiency and avoid major economic losses. However, with the development of technology, the increasing size and complexity of data, and the lack of labels for relevant abnormal data, it is becoming increasingly challenging to perform effective and accurate anomaly detection in high-dimensional and complex data sets. In this paper, we propose a hypergraph based spatiotemporal graph convolutional neural network model STGCN_Hyper, which explicitly captures high-order, multi-hop correlations between multiple variables through a hypergraph based dynamic graph structure learning module. On this basis, we further use the hypergraph based spatiotemporal graph convolutional network to utilize the learned hypergraph structure to effectively propagate and aggregate one-hop and multi-hop related node information in the convolutional network, thereby obtaining rich spatial information. Furthermore, through the multi-scale TCN dilated convolution module, the STGCN_hyper model can also capture the dependencies of features at different scales in the temporal dimension. An unsupervised anomaly detector based on PCA and GMM is also integrated into the STGCN_hyper model. Through the anomaly score of the detector, the model can detect the anomalies in an unsupervised way. Experimental results on multiple time series datasets show that our model can flexibly learn the multi-scale time series features in the data and the dependencies between features, and outperforms most existing baseline models in terms of precision, recall, F1-score on anomaly detection tasks. Our code is available on: https://git.ecdf.ed.ac.uk/msc-23-24/s2044819
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。