Research map / Time series / Long-term forecasting
SVGL: Scale-Variable Graph Learning in Model Space for Multivariate Time Series Classification
Shikang Liu, Ziyu Tang, Xiren Zhou, Huanhuan Chen
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 multi-scale analysis (single scale to multi-scale), no graph learners (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.642 -> 0.716 | Improved |
| add multi-scale analysis to GL+SSL graph learners (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.683 -> 0.762 | Improved |
| add global graph learner on top of multi-scale (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.716 -> 0.742 | Improved |
| add sample-specific graph learner on top of multi-scale (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.716 -> 0.749 | Improved |
| combine global and sample-specific graph learners (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.749 -> 0.762 | Improved |
| increase nearest neighbors k from 8 to 32 (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.739 -> 0.762 | Improved |
| increase k beyond 32 (to 256, near fully connected) (ablation) | SVGL · UEA 30 datasets | average accuracy: 0.762 -> 0.758 | Hurt |
| SVGL vs ModernTCN on EthanolConcentration | SVGL · EthanolConcentration | accuracy (%): 36.3 -> 44.1 | Improved |
| SVGL vs ModernTCN on JapaneseVowels | SVGL · JapaneseVowels | accuracy (%): 98.8 -> 95.4 | Hurt |
| SVGL vs MPTSNet (cross-variable learning per scale) | SVGL · UEA 30 datasets | average accuracy (%): 73.5 -> 76.2 | Improved |
| SVGL vs TimeMIL | SVGL · UEA 30 datasets | average accuracy (%): 75.0 -> 76.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- TimeMIL — TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML 2024) · better on 3 of 4 shared results
- MPTSNet — MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025) · better on 2 of 2 shared results
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · better on 1 of 1 shared result
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
- MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025 · similarity 0.88)
- Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series (ICML 2025 · similarity 0.86)
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML 2024 · similarity 0.85)
- Multi-Scale Dynamic Graph Learning for Time Series Anomaly Detection (Student Abstract) (AAAI 2024 · similarity 0.85)
- MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting (AAAI 2024 · similarity 0.85)
- Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data (AAAI 2024 · 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.
