Research map / Time series / Long-term forecasting
Non-stationary Transformers: Exploring the Stationarity in 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 |
|---|---|---|---|
| apply Non-stationary framework | Transformer · 6 benchmarks | MSE: 49.43% | Helped |
| apply Non-stationary framework | Informer · 6 benchmarks | MSE: 47.34% | Helped |
| apply Non-stationary framework | Autoformer · 6 benchmarks | MSE: 10.57% | Helped |
| apply Non-stationary framework | Transformer · Traffic | MSE: 0.665 -> 0.628 | Helped |
| Non-stationary Transformer vs previous SOTA | Transformer · Exchange horizon 336 | MSE: 0.509 -> 0.421 | Helped |
| add De-stationary Attention on top of Series Stationarization (ablation) | Transformer · ETTm2 | MSE: 0.461 -> 0.306 | Helped |
| add De-stationary Attention on top of Series Stationarization (ablation) | Transformer · Exchange | MSE: 0.569 -> 0.461 | Helped |
| add De-stationary Attention on top of Series Stationarization (ablation) | Reformer · Electricity | MSE: 0.207 -> 0.206 | No clear effect |
| parameter-free Series Stationarization instead of RevIN (ablation) | Transformer · 6 benchmarks | MSE: 0.460 vs 0.461 (ETTm2) | No clear effect |
| add Series Stationarization (ablation) | Transformer · ETTm2 horizon 96 | MSE: 0.572 -> 0.253 | Helped |
| De-stationary Attention without stationarization (ablation) | Transformer · ILI horizon 24 | MSE: 4.748 -> 4.734 | No clear effect |
| re-incorporate non-stationarity in attention instead of feed-forward (ablation) | stationarized Transformer · ETTm2 horizon 96 | MSE: 0.275 -> 0.192 | Mixed |
Closest papers by meaning
- Sequence Complementor: Complementing Transformers for Time Series Forecasting with Learnable Sequences (AAAI 2025 · similarity 0.90)
- Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting (AAAI 2024 · similarity 0.90)
- A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle (ICML 2025 · similarity 0.89)
- SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention (ICML 2024 · similarity 0.89)
- DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching (NeurIPS 2024 · similarity 0.89)
- iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024 · similarity 0.89)
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.