Research map / Time series / Long-term forecasting
Deep Time-Series Forecasting in 10 Years: A Survey
Hao Wang, Licheng Pan, Qingsong Wen, Jialin Yu, Zhichao Chen, Chunyuan Zheng, Xiaoxi Li, Zhixuan Chu, Chao Xu, Mingming Gong, Haoxuan Li, Lu Yuan and 3 more
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 |
|---|---|---|---|
| replace pointwise MSE loss with DistDF | FredFormer · ECL | average MSE: 0.191 -> 0.173 | Improved |
| replace pointwise MSE loss with DBLoss | FredFormer · ECL | average MAE: 0.284 -> 0.264 | Improved |
| replace pointwise MSE loss with QDF | FredFormer · ETTm1 | average MSE: 0.387 -> 0.378 | Improved |
| replace pointwise MSE loss with FreDF | FredFormer · Weather | average MSE: 0.261 -> 0.254 | Improved |
| replace pointwise MSE loss with DBLoss | FredFormer · ETTm1 | average MAE: 0.398 -> 0.388 | Improved |
| replace MSE with Soft-DTW shape-alignment loss | FredFormer · ETTh1 | average MSE: 0.447 -> 0.460 | Hurt |
| replace MSE with DTW shape-alignment loss | FredFormer · ECL | average MSE: 0.191 -> 0.202 | Hurt |
| replace MSE with Dilate loss | FredFormer · ETTh1 | average MSE: 0.447 -> 0.453 | Hurt |
| compare label-autocorrelation losses against each other | FredFormer · ETTm1, ETTh1, ECL, Weather | average MSE and MAE | Mixed |
Closest papers by meaning
- AutoTimes: Autoregressive Time Series Forecasters via Large Language Models (NeurIPS 2024 · similarity 0.89)
- FreDF: Learning to Forecast in the Frequency Domain (ICLR 2025 · similarity 0.88)
- Auto-Regressive Moving Diffusion Models for Time Series Forecasting (AAAI 2025 · similarity 0.87)
- Time-o1: Time-Series Forecasting Needs Transformed Label Alignment (NeurIPS 2025 · similarity 0.87)
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting (NeurIPS 2026 · similarity 0.87)
- WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting (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.
