Research map / Time series / Long-term forecasting
WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting
Yuxin Jia, Youfang Lin, Xinyan Hao, Yan Lin, Shengnan Guo, Huaiyu Wan
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 |
|---|---|---|---|
| inject 10% white noise into training inputs (ablation) | WITRAN · ECL 168-168 | MSE: 0.2397 -> 0.2543 | Hurt |
| inject 10% white noise into training inputs (ablation) | WITRAN · Traffic 168-168 | MSE: 0.1377 -> 0.1409 | Hurt |
| inject 10% white noise into training inputs (ablation) | WITRAN · ETTh1 168-168 | MSE: 0.1105 -> 0.1137 | Hurt |
| inject 10% white noise into training inputs (ablation) | WITRAN · ETTh2 168-168 | MSE: 0.2389 -> 0.2603 | Hurt |
| inject 10% white noise into training inputs (ablation) | WITRAN · Weather 168-168 | MSE: 0.2050 -> 0.2059 | No clear effect |
| inject 10% white noise into training inputs (ablation) | WITRAN · Weather 1440-2880 | MSE: 0.1769 -> 0.1828 | No clear effect |
| inject 5% noise instead of none (ablation) | WITRAN · ECL 1440-2880 | MSE: 0.3359 -> 0.3315 | No clear effect |
| use WITRAN instead of the strongest baseline | WITRAN · long-range forecasting, all datasets | MSE: average MSE reduction of 5.803% | Improved |
| use WITRAN instead of the strongest baseline | WITRAN · ultra-long-range forecasting | MSE: average MSE reduction of 14.275% | Improved |
| use WITRAN instead of best baseline | WITRAN · ECL ultra-long-range | MSE: average MSE reduction of 39.916% | Improved |
| use WITRAN instead of best baseline | WITRAN · ETTh2 long-range | MSE: average MSE reduction of 4.431% | Improved |
| use WITRAN instead of best baseline | WITRAN · ETTh2 ultra-long-range | MSE: average MSE reduction of 2.441% | Improved |
Later papers that compared with this method
2 later accepted papers report WITRAN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting (NeurIPS 2024 · better on 4 of 4 shared results)
- Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting (NeurIPS 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · better on 1 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
- PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting (NeurIPS 2024 · similarity 0.88)
- Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer (ICML 2025 · similarity 0.86)
- HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.85)
- xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories (NeurIPS 2025 · similarity 0.85)
- Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series Forecasting (AAAI 2025 · similarity 0.85)
- Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization (ICML 2025 · similarity 0.85)
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.
