Add to ORKGDiffusion models have been recently used for anomaly detection (AD) in images. In this paper we investigate whether they can also be leveraged for AD on multivariate time series (MTS). We test two diffusion-based models and compare them to several strong neural baselines. We also extend the PA%K protocol, by computing a ROCK-AUC metric, which is agnostic to both the detection threshold and the ratio K of correctly detected points. Our models outperform the baselines on synthetic datasets and are competitive on real-world datasets, illustrating the potential of diffusion-based methods for AD in multivariate time series.Comment: Accepted at the AI4TS workshop of the 23rd IEEE International Conference on Data Mining (ICDM 2023), 9 pages, 7 f...
Anomaly detection in multivariate time series is a major issue in many fields. The increasing comple...
As industries become automated and connectivity technologies advance, a wide range of systems contin...
Low-count time series describe sparse or intermittent events, which are prevalent in large-scale onl...
Anomaly detection in multivariate time series data is of paramount importance for ensuring the effic...
Anomaly detection in time series is a complex task that has been widely studied. In recent years, th...
Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance fo...
Generative models have been shown to provide a powerful mechanism for anomaly detection by learning ...
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, di...
In many real-world applications today, it is critical to continuously record and monitor certain mac...
Numerous methods for time series anomaly detection (TSAD) methods have emerged in recent years. Most...
In medical applications, weakly supervised anomaly detection methods are of great interest, as only ...
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, di...
Modern single-particle-tracking techniques produce extensive time-series of diffusive motion in a wi...
Time series anomaly detection has been a perennially important topic in data science, with papers da...
Anomaly Detection task is to determine critical data points whose behaviour deviates unexpectedly fr...
Anomaly detection in multivariate time series is a major issue in many fields. The increasing comple...
As industries become automated and connectivity technologies advance, a wide range of systems contin...
Low-count time series describe sparse or intermittent events, which are prevalent in large-scale onl...
Anomaly detection in multivariate time series data is of paramount importance for ensuring the effic...
Anomaly detection in time series is a complex task that has been widely studied. In recent years, th...
Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance fo...
Generative models have been shown to provide a powerful mechanism for anomaly detection by learning ...
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, di...
In many real-world applications today, it is critical to continuously record and monitor certain mac...
Numerous methods for time series anomaly detection (TSAD) methods have emerged in recent years. Most...
In medical applications, weakly supervised anomaly detection methods are of great interest, as only ...
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, di...
Modern single-particle-tracking techniques produce extensive time-series of diffusive motion in a wi...
Time series anomaly detection has been a perennially important topic in data science, with papers da...
Anomaly Detection task is to determine critical data points whose behaviour deviates unexpectedly fr...
Anomaly detection in multivariate time series is a major issue in many fields. The increasing comple...
As industries become automated and connectivity technologies advance, a wide range of systems contin...
Low-count time series describe sparse or intermittent events, which are prevalent in large-scale onl...