Research map / Time series / Long-term forecasting
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
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 |
|---|---|---|---|
| Add learned latent correlations rather than use a priori topology (ablation) | StemGNN · PEMS07 15min | MAE: 2.158 -> 2.144 | Helped |
| Add the Spe-Seq Cell (ablation) | StemGNN · PEMS07 15min | MAE: 2.612 -> 2.144 | Helped |
| Add DFT and inverse DFT in the Spe-Seq Cell (ablation) | StemGNN · PEMS07 15min | MAE: 2.299 -> 2.144 | Helped |
| Add GFT to capture graph structure (ablation) | StemGNN · PEMS07 15min | MAE: 2.237 -> 2.144 | Helped |
| Add a residual connection between blocks (ablation) | StemGNN · PEMS07 15min | MAE: 2.256 -> 2.144 | Helped |
| Add the backcasting branch (ablation) | StemGNN · PEMS07 15min | MAE: 2.203 -> 2.144 | Helped |
| Use StemGNN instead of the strongest baseline for each dataset | Multivariate forecasting benchmarks · PEMS08 | MAE: 15.12 -> 15.83 | Hurt |
Closest papers by meaning
- Temporal Query Network for Efficient Multivariate Time Series Forecasting (ICML 2025 · similarity 0.86)
- Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach (ICML 2024 · similarity 0.86)
- Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data (AAAI 2024 · similarity 0.85)
- MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting (AAAI 2024 · similarity 0.84)
- Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series (ICML 2025 · similarity 0.83)
- Revisiting Attention for Multivariate Time Series Forecasting (AAAI 2025 · 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.