Research map / Time series / Anomaly detection
Prototype-oriented unsupervised anomaly detection for multivariate time series
Yuxin Li, Wenchao Chen, Bo Chen, Dongsheng Wang, Long Tian, Mingyuan Zhou
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add prototype-oriented OT (POT) module with global prototypes to the Transformer+VAE model (ablation) | Transformer+VAE · Average over four datasets (ablation, Fig. 3a) | F1: +7.11% average | Improved |
| Add OT-based regularization loss to the Transformer+VAE+POT model (full PUAD) (ablation) | Transformer+VAE+POT · Average over four datasets (ablation, Fig. 3a) | F1: +4.52% average | Improved |
| Use prototype-based one-for-all model with few local prototypes for meta adaptation vs one-for-one baselines | PUAD · Meta anomaly detection (SMD, MSL, SMAP; 1-200 samples) | F1 | Improved |
| Replace per-MTS one-for-one parameters with a single one-for-all model with prototypes (PUAD) and reduced parameter count | PUAD · Parameter count comparison (Fig. 3b) | number of parameters | Improved |
| Prototype-based OT model vs Anomaly Transformer on testing time | PUAD · SMD testing time per sample | testing time per sample (sec x 10^-5): 3.30 vs 8.29 | Improved |
| PUAD vs strongest baselines on standard UAD | PUAD · SMD, MSL, PSM, SMAP, DND (F1) | F1 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Anomaly Transformer — Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy (ICLR 2022) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.89)
- Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing (NeurIPS 2026 · similarity 0.88)
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.87)
- When Model Meets New Normals: Test-Time Adaptation for Unsupervised Time-Series Anomaly Detection (AAAI 2024 · similarity 0.86)
- Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection (NeurIPS 2026 · similarity 0.86)
- SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
