Research map / Label-efficient and robust learning / OOD and anomaly detection
Temporal Anomaly Detection: Calibrating the Surprise
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use time-feature regression to predict expected log-likelihood instead of a single mean log-likelihood (ablation) | TLR · Randomly injected accesses across tested datasets | AUC | Helped |
| Use TLR rather than the compared baselines | Anomalous-time interval swaps · Tested datasets | AUC | Helped |
| Use TLR rather than methods that do not model event timing | Anomalous-time interval swaps · Tested datasets | AUC | Helped |
| Use TLR rather than MEAN's unadjusted average log-likelihood (ablation) | TLR · Randomly injected accesses across tested datasets | AUC | Helped |
| Process intervals individually and reserve matrix optimization for training | TLR · TDA (small) and Amazon (small) | training time (seconds) | Helped |
| Use fast per-interval scoring with the trained model | TLR · TDA, Amazon, MovieLens, Netflix, TDA (small), Amazon (small) | test time (seconds) | Helped |
Closest papers by meaning
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.86)
- Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability. (NeurIPS 2026 · similarity 0.85)
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.83)
- Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection (NeurIPS 2026 · similarity 0.83)
- One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection (NeurIPS 2024 · similarity 0.83)
- When Model Meets New Normals: Test-Time Adaptation for Unsupervised Time-Series Anomaly Detection (AAAI 2024 · similarity 0.83)
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.