Research map / Time series / Long-term forecasting
FeTS: A Feature-Aware Framework for Time Series Forecasting
Le Wang, Jianyong Chen, Songbai 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 AdaFE instead of ordinary CNN (ablation) | FeTS · Avg of 5 datasets | MSE: 0.276 -> 0.264 | Improved |
| add AdaFE instead of removing it (ablation) | FeTS · Avg of 5 datasets | MSE: 0.271 -> 0.264 | Improved |
| add DSFFN instead of ordinary FFN (ablation) | FeTS · Avg of 5 datasets | MSE: 0.274 -> 0.264 | Improved |
| add DSFFN instead of removing it (ablation) | FeTS · Avg of 5 datasets | MSE: 0.272 -> 0.264 | Improved |
| add DSFFN instead of ordinary FFN (ablation) | FeTS · Electricity | MAE: 0.255 -> 0.254 | Hurt |
| add AdaFE after patch embedding | PatchTST · ETTh1 | MSE: 0.484 -> 0.436 | Improved |
| add AdaFE after patch embedding | PatchTST · Solar-Energy | MSE: 0.226 -> 0.204 | Improved |
| add AdaFE after 2D transformation | TimesNet · ETTh2 | MSE: 0.415 -> 0.372 | Improved |
| add AdaFE after 2D transformation | TimesNet · Weather | MAE: 0.285 -> 0.271 | Improved |
| increase patch embedding dimension D from 128 to 512 (ablation) | FeTS · Solar-Energy | MSE: 0.183 -> 0.193 | Hurt |
| increase patch embedding dimension D from 32 to 128 (ablation) | FeTS · Solar-Energy | MSE: 0.188 -> 0.183 | Improved |
| use FeTS instead of iTransformer | FeTS · Traffic | MSE: 0.401 vs 0.395 | Hurt |
Closest papers by meaning
- SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series (NeurIPS 2025 · similarity 0.87)
- ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning (ICLR 2024 · similarity 0.87)
- Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift (NeurIPS 2025 · similarity 0.87)
- FilterNet: Harnessing Frequency Filters for Time Series Forecasting (NeurIPS 2024 · similarity 0.87)
- CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables (ICML 2024 · similarity 0.87)
- Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer (ICML 2025 · 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.
