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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add seen abnormality learning (L_seen) (ablation) | IMPACT · TUSZ (general) | AUC (%): 70.91 -> 82.91 | Improved |
| add unseen abnormality learning (L_unseen) (ablation) | IMPACT · TUSZ (hard) | AUC (%): 60.92 -> 75.70 | Improved |
| add unseen abnormality learning (L_unseen) (ablation) | IMPACT · UCR (general) | AUC (%): 59.27 -> 59.21 | No clear effect |
| add label-flipped contaminated samples D_con' (ablation) | IMPACT · TUSZ (hard) | AUC (%): 72.64 -> 75.70 | Improved |
| add feature deviation score s_f to anomaly score (ablation) | IMPACT · TUSZ (general) | AUC (%): 74.18 -> 82.91 | Improved |
| add feature deviation score s_f (ablation) | IMPACT · SAD (general) | AUC (%): 68.04 -> 68.13 | No clear effect |
| flip labels of influence-identified contaminated samples instead of using unflipped D_con (ablation) | IMPACT · TUSZ (general) | AUC (%): 71.37 -> 82.91 | Improved |
| use influence-guided reference set instead of random D_ref (ablation) | IMPACT · PTBXL (hard) | AUC (%): 51.56 -> 62.48 | Improved |
| use influence-guided label flipping instead of random flipping (ablation) | IMPACT · TUSZ (general) | AUC (%): 72.43 -> 82.91 | Improved |
| use influence-guided feature perturbation instead of random Gaussian perturbation (ablation) | IMPACT · TUSZ (hard) | AUC (%): 62.87 -> 75.70 | Improved |
| increase unseen-abnormality loss weight lambda (ablation) | IMPACT · hard setting | AUC (%) | Improved |
| increase number of perturbed samples k (ablation) | IMPACT · hard setting | AUC (%) | Mixed |
Closest papers by meaning
- Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection (CVPR 2024 · similarity 0.88)
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.87)
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.87)
- Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability. (NeurIPS 2026 · similarity 0.86)
- Channel Matters: Estimating Channel Influence for Multivariate Time Series (NeurIPS 2025 · similarity 0.86)
- Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing (NeurIPS 2026 · 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.
