Research map / Time series / Long-term forecasting
Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
Fanpu Cao, Lu Dai, Jindong Han, Hui Xiong
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 GTR module (ablation) | MLP backbone · PEMS03 | MSE: 0.135 -> 0.087 | Improved |
| add GTR module (ablation) | MLP backbone · PEMS04 | MSE: 0.151 -> 0.087 | Improved |
| add GTR module (ablation) | MLP backbone · Electricity | MSE: 0.190 -> 0.166 | Improved |
| add GTR module (ablation) | iTransformer · PEMS03 | MSE: 0.159 -> 0.098 | Improved |
| add GTR module (ablation) | iTransformer · PEMS04 | MSE: 0.120 -> 0.087 | Improved |
| add GTR module (ablation) | iTransformer · Electricity | MSE: 0.175 -> 0.162 | Improved |
| add GTR module (ablation) | PatchTST · PEMS04 | MSE: 0.150 -> 0.096 | Improved |
| add GTR module (ablation) | DLinear · PEMS04 | MSE: 0.261 -> 0.136 | Improved |
| add GTR module (ablation) | DLinear · Electricity | MSE: 0.210 -> 0.169 | Improved |
| use GTR MLP instead of SOFTS/S-Mamba/iTransformer | GTR · Traffic | MSE: 0.470 vs 0.409 (SOFTS) | Hurt |
| use GTR MLP instead of CycleNet | GTR · Solar-Energy | MSE: 0.210 -> 0.194 | Improved |
| use shorter look-back window | baselines vs GTR · Electricity / Solar-Energy | error | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- TimeMixer — TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting (ICLR 2024) · better on 1 of 1 shared result
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · better on 1 of 1 shared result
- SOFTS — SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion (NeurIPS 2024) · better on 0 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
- ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning (ICLR 2024 · similarity 0.89)
- TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data (AAAI 2025 · similarity 0.88)
- TiRex-2: Generalizing TiRex to Multivariate Data and Streaming (NeurIPS 2026 · similarity 0.88)
- TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting (ICML 2025 · similarity 0.88)
- Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift (NeurIPS 2025 · similarity 0.88)
- OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain (NeurIPS 2025 · similarity 0.88)
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.
