AI Paper Atlas

Research map / Time series / Anomaly detection

IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection

Xiaohui Zhou, Yijie Wang, Hongzuo Xu, Weixuan Liang, Xiaoli Li, Guansong Pang

ICML 2026 · Time series › Anomaly detection · approach: Time series anomaly detection evaluation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 seen abnormality learning (L_seen) (ablation)IMPACT · TUSZ (general)AUC (%): 70.91 -> 82.91Improved
add unseen abnormality learning (L_unseen) (ablation)IMPACT · TUSZ (hard)AUC (%): 60.92 -> 75.70Improved
add unseen abnormality learning (L_unseen) (ablation)IMPACT · UCR (general)AUC (%): 59.27 -> 59.21No clear effect
add label-flipped contaminated samples D_con' (ablation)IMPACT · TUSZ (hard)AUC (%): 72.64 -> 75.70Improved
add feature deviation score s_f to anomaly score (ablation)IMPACT · TUSZ (general)AUC (%): 74.18 -> 82.91Improved
add feature deviation score s_f (ablation)IMPACT · SAD (general)AUC (%): 68.04 -> 68.13No clear effect
flip labels of influence-identified contaminated samples instead of using unflipped D_con (ablation)IMPACT · TUSZ (general)AUC (%): 71.37 -> 82.91Improved
use influence-guided reference set instead of random D_ref (ablation)IMPACT · PTBXL (hard)AUC (%): 51.56 -> 62.48Improved
use influence-guided label flipping instead of random flipping (ablation)IMPACT · TUSZ (general)AUC (%): 72.43 -> 82.91Improved
use influence-guided feature perturbation instead of random Gaussian perturbation (ablation)IMPACT · TUSZ (hard)AUC (%): 62.87 -> 75.70Improved
increase unseen-abnormality loss weight lambda (ablation)IMPACT · hard settingAUC (%)Improved
increase number of perturbed samples k (ablation)IMPACT · hard settingAUC (%)Mixed

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