Research map / Time series / Long-term forecasting
APT: Affine Prototype-Timestamp for Time Series Forecasting Under Distribution Shift
Yujie Li, Zezhi Shao, Chengqing Yu, Yisong Fu, Tao Sun, Yongjun Xu, Fei Wang
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 APT plug-in | Informer+RevIN · ETTh2 | MSE: 0.658 -> 0.531 | Improved |
| add APT plug-in | Informer+RevIN · Exchange | MSE: 0.587 -> 0.460 | Improved |
| add APT plug-in | iTransformer+RevIN · ETTh1 | MSE: 0.485 -> 0.441 | Improved |
| add APT plug-in | SparseTSF+RevIN · ETTh2 | MSE: 0.399 -> 0.470 | Hurt |
| add APT plug-in | CATS+RevIN · ECL | MSE: 0.165 -> 0.166 | No clear effect |
| add APT plug-in | SparseTSF+RevIN · ETTh1 | MSE: 0.427 -> 0.424 | No clear effect |
| add APT plug-in | SparseTSF+SAN · ETTh2 | MSE: 0.619 -> 0.478 | Improved |
| add pretraining losses (full APT) vs skipping APT pretraining (ablation) | APT · Exchange iTransformer | MSE: 0.785 -> 0.445 | Improved |
| add loss weight lambda (ablation) | APT · Exchange iTransformer | MSE: 0.6549 -> 0.445 | Improved |
| add load balancing loss (ablation) | APT · Exchange iTransformer | MSE: 0.531 -> 0.445 | Improved |
| add orthogonal loss (ablation) | APT · ETTh1 Informer | MSE: 1.215 -> 1.121 | Improved |
| add affine regularization loss (ablation) | APT · ETTh1 Informer | MSE: 1.121 -> 1.121 | No clear effect |
Closest papers by meaning
- TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data (AAAI 2025 · similarity 0.86)
- PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting (NeurIPS 2026 · similarity 0.86)
- ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons (NeurIPS 2024 · similarity 0.85)
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting (NeurIPS 2025 · similarity 0.84)
- Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling (ICML 2025 · similarity 0.84)
- HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.84)
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.
