Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917538498084864 |
|---|---|
| author | Wei, Junhao Li, Yanxiao Chen, Bidong Zhao, Yifu Li, Haochen Yao, Dexing Lu, Baili Ye, Xudong Feng, Jietian Im, Sio-Kei Wang, Yapeng Yang, Xu |
| author_facet | Wei, Junhao Li, Yanxiao Chen, Bidong Zhao, Yifu Li, Haochen Yao, Dexing Lu, Baili Ye, Xudong Feng, Jietian Im, Sio-Kei Wang, Yapeng Yang, Xu |
| contents | We present a unified experiment, analysis, and benchmark study of multivariate time-series (MTS) anomaly detection. Ten family-representative detectors -- spanning statistical, reconstruction, association, frequency, and generic-transformer families -- are evaluated on five datasets (SMD, MSL, SMAP, PSM, and MSDS) under effectiveness, efficiency, robustness, and cross-dataset generalisation. All methods share the same windowing, scoring, hardware, and metric protocols. Effectiveness, ablation, and robustness use three random seeds; cross-dataset transfer uses seed~0 because each extra seed requires $250$ source-target evaluations. The benchmark yields three method-independent findings: no single-bias baseline dominates; absolute perturbation VUS-ROC is more informative than retention ratios; and MSDS behaves as an event-dense deployment workload rather than a sparse point-anomaly benchmark. Under this protocol we also introduce \ours{}, an adaptive detector family combining a NOTEARS-constrained directed channel-graph view with optional patch-attention and temporal-association views. \ours{} achieves the best macro-average VUS-ROC ($0.675$, $+5.1$~pt over the second-best LSTM-AE), ranks first overall, and reaches the top-3 on all five datasets. Its wins on MSL and MSDS are narrow, while its average and robustness gains are larger: under the same three-seed robustness protocol for every method, it obtains the strongest absolute VUS-ROC across noise, channel dropout, and time-shift perturbations. We release the MSDS preprocessing protocol, configurations, scripts, and seed-level metric dumps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28103 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector Wei, Junhao Li, Yanxiao Chen, Bidong Zhao, Yifu Li, Haochen Yao, Dexing Lu, Baili Ye, Xudong Feng, Jietian Im, Sio-Kei Wang, Yapeng Yang, Xu Machine Learning Computer Science and Game Theory We present a unified experiment, analysis, and benchmark study of multivariate time-series (MTS) anomaly detection. Ten family-representative detectors -- spanning statistical, reconstruction, association, frequency, and generic-transformer families -- are evaluated on five datasets (SMD, MSL, SMAP, PSM, and MSDS) under effectiveness, efficiency, robustness, and cross-dataset generalisation. All methods share the same windowing, scoring, hardware, and metric protocols. Effectiveness, ablation, and robustness use three random seeds; cross-dataset transfer uses seed~0 because each extra seed requires $250$ source-target evaluations. The benchmark yields three method-independent findings: no single-bias baseline dominates; absolute perturbation VUS-ROC is more informative than retention ratios; and MSDS behaves as an event-dense deployment workload rather than a sparse point-anomaly benchmark. Under this protocol we also introduce \ours{}, an adaptive detector family combining a NOTEARS-constrained directed channel-graph view with optional patch-attention and temporal-association views. \ours{} achieves the best macro-average VUS-ROC ($0.675$, $+5.1$~pt over the second-best LSTM-AE), ranks first overall, and reaches the top-3 on all five datasets. Its wins on MSL and MSDS are narrow, while its average and robustness gains are larger: under the same three-seed robustness protocol for every method, it obtains the strongest absolute VUS-ROC across noise, channel dropout, and time-shift perturbations. We release the MSDS preprocessing protocol, configurations, scripts, and seed-level metric dumps. |
| title | Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector |
| topic | Machine Learning Computer Science and Game Theory |
| url | https://arxiv.org/abs/2605.28103 |