Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912073875718144 |
|---|---|
| author | Zhao, Sinong Wang, Wenrui Xu, Hongzuo Yu, Zhaoyang Wen, Qingsong Wang, Gang Liu, xiaoguang Pang, Guansong |
| author_facet | Zhao, Sinong Wang, Wenrui Xu, Hongzuo Yu, Zhaoyang Wen, Qingsong Wang, Gang Liu, xiaoguang Pang, Guansong |
| contents | Identifying anomalies from time series data plays an important role in various fields such as infrastructure security, intelligent operation and maintenance, and space exploration. Current research focuses on detecting the anomalies after they occur, which can lead to significant financial/reputation loss or infrastructure damage. In this work we instead study a more practical yet very challenging problem, time series anomaly prediction, aiming at providing early warnings for abnormal events before their occurrence. To tackle this problem, we introduce a novel principled approach, namely future context modeling (FCM). Its key insight is that the future abnormal events in a target window can be accurately predicted if their preceding observation window exhibits any subtle difference to normal data. To effectively capture such differences, FCM first leverages long-term forecasting models to generate a discriminative future context based on the observation data, aiming to amplify those subtle but unusual difference. It then models a normality correlation of the observation data with the forecasting future context to complement the normality modeling of the observation data in foreseeing possible abnormality in the target window. A joint variate-time attention learning is also introduced in FCM to leverage both temporal signals and features of the time series data for more discriminative normality modeling in the aforementioned two views. Comprehensive experiments on five datasets demonstrate that FCM gains good recall rate (70\%+) on multiple datasets and significantly outperforms all baselines in F1 score. Code is available at https://github.com/mala-lab/FCM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12206 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling Zhao, Sinong Wang, Wenrui Xu, Hongzuo Yu, Zhaoyang Wen, Qingsong Wang, Gang Liu, xiaoguang Pang, Guansong Machine Learning Artificial Intelligence Identifying anomalies from time series data plays an important role in various fields such as infrastructure security, intelligent operation and maintenance, and space exploration. Current research focuses on detecting the anomalies after they occur, which can lead to significant financial/reputation loss or infrastructure damage. In this work we instead study a more practical yet very challenging problem, time series anomaly prediction, aiming at providing early warnings for abnormal events before their occurrence. To tackle this problem, we introduce a novel principled approach, namely future context modeling (FCM). Its key insight is that the future abnormal events in a target window can be accurately predicted if their preceding observation window exhibits any subtle difference to normal data. To effectively capture such differences, FCM first leverages long-term forecasting models to generate a discriminative future context based on the observation data, aiming to amplify those subtle but unusual difference. It then models a normality correlation of the observation data with the forecasting future context to complement the normality modeling of the observation data in foreseeing possible abnormality in the target window. A joint variate-time attention learning is also introduced in FCM to leverage both temporal signals and features of the time series data for more discriminative normality modeling in the aforementioned two views. Comprehensive experiments on five datasets demonstrate that FCM gains good recall rate (70\%+) on multiple datasets and significantly outperforms all baselines in F1 score. Code is available at https://github.com/mala-lab/FCM. |
| title | Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.12206 |