Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913659115012096 |
|---|---|
| author | Wang, Yaxuan Cheng, Hao Xiong, Jing Wen, Qingsong Jia, Han Song, Ruixuan Zhang, Liyuan Zhu, Zhaowei Liu, Yang |
| author_facet | Wang, Yaxuan Cheng, Hao Xiong, Jing Wen, Qingsong Jia, Han Song, Ruixuan Zhang, Liyuan Zhu, Zhaowei Liu, Yang |
| contents | Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level labels (detected abnormal events with segments of time points) and unlabeled data (undetected events), while the ideal algorithmic outcome should be point-level predictions. Therefore, the huge label information gap between training data and targets makes the task challenging. In this study, we formulate the above imperfect information as noisy labels and propose NRdetector, a noise-resilient framework that incorporates confidence-based sample selection, robust segment-level learning, and data-centric point-level detection for multivariate time series anomaly detection. Particularly, to bridge the information gap between noisy segment-level labels and missing point-level labels, we develop a novel loss function that can effectively mitigate the label noise and consider the temporal features. It encourages the smoothness of consecutive points and the separability of points from segments with different labels. Extensive experiments on real-world multivariate time series datasets with 11 different evaluation metrics demonstrate that NRdetector consistently achieves robust results across multiple real-world datasets, outperforming various baselines adapted to operate in our setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11959 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels Wang, Yaxuan Cheng, Hao Xiong, Jing Wen, Qingsong Jia, Han Song, Ruixuan Zhang, Liyuan Zhu, Zhaowei Liu, Yang Machine Learning Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level labels (detected abnormal events with segments of time points) and unlabeled data (undetected events), while the ideal algorithmic outcome should be point-level predictions. Therefore, the huge label information gap between training data and targets makes the task challenging. In this study, we formulate the above imperfect information as noisy labels and propose NRdetector, a noise-resilient framework that incorporates confidence-based sample selection, robust segment-level learning, and data-centric point-level detection for multivariate time series anomaly detection. Particularly, to bridge the information gap between noisy segment-level labels and missing point-level labels, we develop a novel loss function that can effectively mitigate the label noise and consider the temporal features. It encourages the smoothness of consecutive points and the separability of points from segments with different labels. Extensive experiments on real-world multivariate time series datasets with 11 different evaluation metrics demonstrate that NRdetector consistently achieves robust results across multiple real-world datasets, outperforming various baselines adapted to operate in our setting. |
| title | Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.11959 |