AI Paper Atlas

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

ICML 2023 · Time series › Anomaly detection · approach: Multivariate anomaly detection

Read the paper

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 changedWhereMeasuredEffect
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% averageImproved
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% averageImproved
Use prototype-based one-for-all model with few local prototypes for meta adaptation vs one-for-one baselinesPUAD · Meta anomaly detection (SMD, MSL, SMAP; 1-200 samples)F1Improved
Replace per-MTS one-for-one parameters with a single one-for-all model with prototypes (PUAD) and reduced parameter countPUAD · Parameter count comparison (Fig. 3b)number of parametersImproved
Prototype-based OT model vs Anomaly Transformer on testing timePUAD · SMD testing time per sampletesting time per sample (sec x 10^-5): 3.30 vs 8.29Improved
PUAD vs strongest baselines on standard UADPUAD · SMD, MSL, PSM, SMAP, DND (F1)F1Mixed

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy