Research map / Time series / Anomaly detection
State-Derivative-Aware Neural Controlled Differential Equations for Multivariate Time Series Anomaly Detection and Diagnosis
Xin Sun, Heng Zhou, Yuhao Wu, Chao Li
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 state-derivative reconstruction error to time-point error for scoring (ablation) | SDA2D · 4 datasets (avg) | VUS-PR: 0.2532 -> 0.2784 | Improved |
| add time-point reconstruction error to derivative error for scoring (ablation) | SDA2D · 4 datasets (avg) | VUS-PR: 0.2609 -> 0.2784 | Improved |
| add spatial branch to time-only features (ablation) | SDA2D · 4 datasets (avg) | VUS-PR: 0.2633 -> 0.2784 | Improved |
| add temporal branch to spatial-only features (ablation) | SDA2D · 4 datasets (avg) | VUS-PR: 0.2611 -> 0.2784 | Improved |
| add time-spatial interaction (ablation) | SDA2D · 4 datasets (avg) | VUS-PR: 0.2707 -> 0.2784 | Improved |
| use SDA2D instead of CATCH | SDA2D · MSL | VUS-PR: 0.0331 -> 0.2829 | Improved |
| use SDA2D instead of OFA | SDA2D · SMAP | VUS-PR: 0.2929 -> 0.4981 | Improved |
| use SDA2D instead of CAE-M | SDA2D · SWaT | VUS-PR: 0.1804 -> 0.2095 | Improved |
| use SDA2D instead of FITS | SDA2D · TAO | VUS-PR: 0.0784 -> 0.1232 | Improved |
| use SDA2D instead of OmniAnomaly | SDA2D · SMAP | VUS-ROC: 0.9111 -> 0.8828 | Hurt |
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.
- CATCH — CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching (ICLR 2025) · better on 2 of 2 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 0.87)
- SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series (NeurIPS 2024 · similarity 0.86)
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.85)
- Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing (NeurIPS 2026 · similarity 0.85)
- STAR: Boosting Time Series Foundation Models for Anomaly Detection Through State-Aware Adapter (NeurIPS 2026 · similarity 0.85)
- COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection (NeurIPS 2026 · similarity 0.84)
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.
