Research map / Time series / Long-term forecasting
CATN: Cross Attentive Tree-Aware 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 |
|---|---|---|---|
| Use CATN's tree construction and embedding to model hierarchical and grouped series correlations (ablation) | CATN · Electricity, horizon 3 | RMSE: 0.3173 -> 0.2601 | Helped |
| Use global-and-local learning instead of a recurrent module alone (ablation) | CATN · Electricity, horizon 3 | RMSE: 0.2603 -> 0.2601 | Helped |
| Add the cross-attention mechanism (ablation) | CATN · Electricity, horizon 3 | MAE: 0.0615 -> 0.061 | Helped |
| Use CATN rather than TPA-LSTM | multivariate forecasting · Traffic, horizon 3 | MAE: 0.0187 -> 0.018 | Helped |
| Use CATN rather than TPA-LSTM | multivariate forecasting · Electricity, horizon 3 | MAE: 0.0617 -> 0.061 | Helped |
| Use CATN rather than DeepGLO | multivariate forecasting · PeMSD7(M), horizon 3 | WAPE: 0.0818 -> 0.0444 | Helped |
| Use CATN rather than MTGNN | multivariate forecasting · METR-LA, horizon 3 | WAPE: 0.0972 -> 0.0516 | Helped |
| Set the embedding dimension to 32 rather than excessively small or large values | CATN · Electricity | MAE | Mixed |
| Use the third interaction layer's nodes as GLL input | CATN · Electricity | MAE | Hurt |
Closest papers by meaning
- CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables (ICML 2024 · similarity 0.86)
- Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series (ICML 2025 · similarity 0.86)
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting (NeurIPS 2026 · similarity 0.86)
- TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data (AAAI 2025 · similarity 0.86)
- MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting (AAAI 2024 · similarity 0.86)
- Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling (ICML 2024 · 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.