Research map / Time series / Anomaly detection
A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
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 MSCRED instead of LSTM-ED | Unsupervised multivariate time-series anomaly detection · Synthetic Data | F1: 0.72 -> 0.89 | Helped |
| Use MSCRED instead of LSTM-ED | Unsupervised multivariate time-series anomaly detection · Power Plant Data | F1: 0.71 -> 0.82 | Helped |
| Add the first three ConvLSTM layers (ablation) | MSCRED · Synthetic Data | F1: 0.29 -> 0.89 | Helped |
| Add the first two ConvLSTM layers (ablation) | MSCRED · Synthetic Data | F1: 0.59 -> 0.89 | Helped |
| Add the attention module (ablation) | MSCRED · Synthetic Data | F1: 0.78 -> 0.89 | Helped |
| Add the first three ConvLSTM layers (ablation) | MSCRED · Power Plant Data | F1: 0.61 -> 0.82 | Helped |
| Add the first two ConvLSTM layers (ablation) | MSCRED · Power Plant Data | F1: 0.76 -> 0.82 | Helped |
| Add the attention module (ablation) | MSCRED · Power Plant Data | F1: 0.78 -> 0.82 | Helped |
| Use MSCRED rather than ARMA or LSTM-ED as input noise varies | Synthetic time-series anomaly detection · Synthetic data with noise scale 0.2 to 0.45 | Precision and Recall | Helped |
| Use MSCRED instead of LSTM-ED for root-cause ranking | Root cause identification · Synthetic and Power Plant Data | Recall@3: 25.9%; 32.4% | Helped |
Closest papers by meaning
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.88)
- Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection (AAAI 2025 · similarity 0.88)
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.87)
- Position: Quo Vadis, Unsupervised Time Series Anomaly Detection? (ICML 2024 · similarity 0.87)
- Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders (ICLR 2025 · similarity 0.87)
- COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection (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.