Research map / Time series / Long-term forecasting
Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting
Xiangfei Qiu, Kangjia Yan, Xvyuan Liu, Xingjian Wu, Jilin Hu
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 Global Frequency Module (learnable NUDFT) (ablation) | TFMixer · MIMIC | MSE: 0.4211 -> 0.4182 | Improved |
| add Global Frequency Module (learnable NUDFT) (ablation) | TFMixer · HumanActivity | MSE: 0.0430 -> 0.0415 | Improved |
| add Local Time Module (ablation) | TFMixer · MIMIC | MSE: 0.5454 -> 0.4182 | Improved |
| add Local Time Module (ablation) | TFMixer · PhysioNet | MSE: 0.3542 -> 0.3118 | Improved |
| add query-based patch mixing (ablation) | TFMixer · MIMIC | MSE: 0.4478 -> 0.4182 | Improved |
| add query-based patch mixing (ablation) | TFMixer · PhysioNet | MSE: 0.3188 -> 0.3118 | Improved |
| add reconstruction loss (ablation) | TFMixer · HumanActivity | MSE: 0.0445 -> 0.0415 | Improved |
| add reconstruction loss (ablation) | TFMixer · MIMIC | MSE: 0.4190 -> 0.4182 | No clear effect |
| add spectrum refinement MLP (ablation) | TFMixer · USHCN | MSE: 0.1519 -> 0.1448 | Improved |
| add spectrum refinement MLP (ablation) | TFMixer · HumanActivity | MSE: 0.0420 -> 0.0415 | No clear effect |
| increase model dimension (ablation) | TFMixer · small datasets (HumanActivity, USHCN) | MSE | Hurt |
| increase model dimension (ablation) | TFMixer · large datasets (PhysioNet, MIMIC) | MSE | Improved |
Closest papers by meaning
- TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting (ICLR 2024 · similarity 0.90)
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting (NeurIPS 2025 · similarity 0.89)
- Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series (NeurIPS 2025 · similarity 0.89)
- OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain (NeurIPS 2025 · similarity 0.89)
- TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting (ICML 2025 · similarity 0.89)
- TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis (AAAI 2025 · 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.
