Research map / Time series / Causal and generative time series
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
Yangyou Liu, Zezhi Shao, Xinyu Chen, Hu Chen, Fei Wang, Yuankai Wu
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 Phase Anchor disentanglement (ablation) | PULSE (MLP) · Average over 8 datasets | MSE: 0.326 -> 0.306 | Improved |
| Add Phase Router (ablation) | PULSE (MLP) · Average over 8 datasets | MSE: 0.315 -> 0.306 | Improved |
| Add Statistic-Aware Mixup (SAM) (ablation) | PULSE (MLP) · Average over 8 datasets | MSE: 0.314 -> 0.306 | Improved |
| Add Statistic-Aware mechanism (ablation) | PULSE (MLP) · Average over 8 datasets | MSE: 0.313 -> 0.306 | Improved |
| Add SAM (ablation) | PULSE (MLP) · Electricity | MSE: 0.160 -> 0.160 | No clear effect |
| Plug PULSE into DLinear | DLinear · ETTh2 | MSE: 0.559 -> 0.373 | Improved |
| Plug PULSE into DLinear | DLinear · Solar | MSE: 0.330 -> 0.216 | Improved |
| Plug PULSE into TimesNet | TimesNet · Solar | MSE: 0.301 -> 0.203 | Improved |
| Plug PULSE into iTransformer | iTransformer · Solar | MSE: 0.233 -> 0.193 | Improved |
| Plug PULSE into PatchTST | PatchTST · Traffic | MSE: 0.481 -> 0.565 | Hurt |
| Plug PULSE into PatchTST | PatchTST · Solar | MSE: 0.270 -> 0.216 | Improved |
| Plug PULSE into iTransformer | iTransformer · Traffic | MSE: 0.428 -> 0.424 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · better on 4 of 5 shared results
- CFPT — CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling (ICML 2025) · better on 3 of 3 shared results
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · better on 2 of 2 shared results
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
- TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra (NeurIPS 2026 · similarity 0.87)
- Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators (NeurIPS 2026 · similarity 0.86)
- Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes (ICML 2024 · similarity 0.86)
- Non-stationary Diffusion For Probabilistic Time Series Forecasting (ICML 2025 · similarity 0.86)
- ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space (NeurIPS 2026 · similarity 0.86)
- Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective (NeurIPS 2024 · 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.
