Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.00415 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918005973188608 |
|---|---|
| author | Lan, Tian Gao, Yifei Lu, Yimeng Zhang, Chen |
| author_facet | Lan, Tian Gao, Yifei Lu, Yimeng Zhang, Chen |
| contents | Unsupervised Time series anomaly detection plays a crucial role in applications across industries. However, existing methods face significant challenges due to data distributional shifts across different domains, which are exacerbated by the non-stationarity of time series over time. Existing models fail to generalize under multiple heterogeneous source domains and emerging unseen new target domains. To fill the research gap, we introduce CICADA (Cross-domain Interpretable Coding for Anomaly Detection and Adaptation), with four key innovations: (1) a mixture of experts (MOE) framework that captures domain-agnostic anomaly features with high flexibility and interpretability; (2) a novel selective meta-learning mechanism to prevent negative transfer between dissimilar domains, (3) an adaptive expansion algorithm for emerging heterogeneous domain expansion, and (4) a hierarchical attention structure that quantifies expert contributions during fusion to enhance interpretability further.Extensive experiments on synthetic and real-world industrial datasets demonstrate that CICADA outperforms state-of-the-art methods in both cross-domain detection performance and interpretability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00415 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series Lan, Tian Gao, Yifei Lu, Yimeng Zhang, Chen Machine Learning Unsupervised Time series anomaly detection plays a crucial role in applications across industries. However, existing methods face significant challenges due to data distributional shifts across different domains, which are exacerbated by the non-stationarity of time series over time. Existing models fail to generalize under multiple heterogeneous source domains and emerging unseen new target domains. To fill the research gap, we introduce CICADA (Cross-domain Interpretable Coding for Anomaly Detection and Adaptation), with four key innovations: (1) a mixture of experts (MOE) framework that captures domain-agnostic anomaly features with high flexibility and interpretability; (2) a novel selective meta-learning mechanism to prevent negative transfer between dissimilar domains, (3) an adaptive expansion algorithm for emerging heterogeneous domain expansion, and (4) a hierarchical attention structure that quantifies expert contributions during fusion to enhance interpretability further.Extensive experiments on synthetic and real-world industrial datasets demonstrate that CICADA outperforms state-of-the-art methods in both cross-domain detection performance and interpretability. |
| title | CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.00415 |