Research map / Time series / Anomaly detection
Finding Time Series Anomalies Using Granular-Ball Vector Data Description
Lifeng Shen, Liang Peng, Ruiwen Liu, Shuyin Xia, Yi Liu
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 granular-ball pruning (ablation) | GBOC · SMD | VUS-PR: 0.781 -> 0.831 | Improved |
| add granular-ball pruning (ablation) | GBOC · YAHOO | VUS-PR: 0.795 -> 0.991 | Improved |
| add granular-ball pruning (ablation) | GBOC · WSD | VUS-PR: 0.885 -> 0.963 | Improved |
| use granular-ball computing instead of K-Means (ablation) | GBOC · SMD | VUS-PR: 0.755 -> 0.781 | Improved |
| use granular-ball computing instead of K-Means (no pruning) (ablation) | GBOC · YAHOO and WSD | VUS-PR: 0.823 -> 0.795 (YAHOO); 0.911 -> 0.885 (WSD) | Hurt |
| add granular-ball loss Lgb (ablation) | GBOC · YAHOO | VUS-PR: 0.869 -> 0.991 | Improved |
| add reconstruction loss Lrec (ablation) | GBOC · YAHOO | VUS-PR: 0.701 -> 0.991 | Improved |
| add reconstruction loss Lrec (ablation) | GBOC · WSD | VUS-PR: 0.945 -> 0.963 | Improved |
| use GBOC instead of KShapeAD under noise-only | GBOC · Type III (YAHOO) | VUS-PR: 0.802 -> 0.952 | Improved |
| use GBOC instead of KShapeAD under drift and noise | GBOC · Type IV (YAHOO) | VUS-PR: 0.624 -> 0.921 | Improved |
| use GBOC instead of KShapeAD under drift-only | GBOC · Type II (SMAP) | VUS-PR: 0.982 -> 0.977 | No clear effect |
Closest papers by meaning
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.86)
- Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection (AAAI 2025 · similarity 0.85)
- Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability. (NeurIPS 2026 · similarity 0.85)
- Multi-Scale Dynamic Graph Learning for Time Series Anomaly Detection (Student Abstract) (AAAI 2024 · similarity 0.85)
- VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection (NeurIPS 2026 · similarity 0.85)
- Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection (NeurIPS 2026 · similarity 0.85)
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.
