TShape: Rescuing Machine Learning Models from Complex Shapelet Anomalies
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911187688488960 |
|---|---|
| author | Cui, Hang Li, Jingjing Si, Haotian Zhou, Quan Pei, Changhua Xie, Gaogang Pei, Dan |
| author_facet | Cui, Hang Li, Jingjing Si, Haotian Zhou, Quan Pei, Changhua Xie, Gaogang Pei, Dan |
| contents | Time series anomaly detection (TSAD) is critical for maintaining the reliability of modern IT infrastructures, where complex anomalies frequently arise in highly dynamic environments. In this paper, we present TShape, a novel framework designed to address the challenges in industrial time series anomaly detection. Existing methods often struggle to detect shapelet anomalies that manifest as complex shape deviations, which appear obvious to human experts but prove challenging for machine learning algorithms. TShape introduces a patch-wise dual attention mechanism with multi-scale convolution to model intricate sub-sequence variations by balancing local, fine-grained shape features with global contextual dependencies. Our extensive evaluation on five diverse benchmarks demonstrates that TShape outperforms existing state-of-the-art models, achieving an average 10\% F1 score improvement in anomaly detection. Additionally, ablation studies and attention visualizations confirm the essential contributions of each component, highlighting the robustness and adaptability of TShape to complex shapelet shapes in time series data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00680 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TShape: Rescuing Machine Learning Models from Complex Shapelet Anomalies Cui, Hang Li, Jingjing Si, Haotian Zhou, Quan Pei, Changhua Xie, Gaogang Pei, Dan Software Engineering Time series anomaly detection (TSAD) is critical for maintaining the reliability of modern IT infrastructures, where complex anomalies frequently arise in highly dynamic environments. In this paper, we present TShape, a novel framework designed to address the challenges in industrial time series anomaly detection. Existing methods often struggle to detect shapelet anomalies that manifest as complex shape deviations, which appear obvious to human experts but prove challenging for machine learning algorithms. TShape introduces a patch-wise dual attention mechanism with multi-scale convolution to model intricate sub-sequence variations by balancing local, fine-grained shape features with global contextual dependencies. Our extensive evaluation on five diverse benchmarks demonstrates that TShape outperforms existing state-of-the-art models, achieving an average 10\% F1 score improvement in anomaly detection. Additionally, ablation studies and attention visualizations confirm the essential contributions of each component, highlighting the robustness and adaptability of TShape to complex shapelet shapes in time series data. |
| title | TShape: Rescuing Machine Learning Models from Complex Shapelet Anomalies |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2510.00680 |