Research map / Time series / Long-term forecasting
Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition
Dongyuan Li, Shun Zheng, Chang Xu, Jiang Bian, Renhe Jiang
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 xCPD plugin to backbones | TSMixer, DLinear, PatchTST, TimesNet · 9 long-term forecasting datasets | MSE/MAE: DLinear Traffic avg MSE 0.625 -> 0.606 | Improved |
| add xCPD instead of CCM or LIFT | DLinear · Traffic avg | MSE: CCM 0.614 / LIFT 0.620 -> 0.606 | Improved |
| use xCPD vs CCM on ETTm2 | PatchTST · ETTm2 avg | MSE: CCM 0.306 vs xCPD 0.340 | Hurt |
| add shared Fourier basis (ablation) | DLinear+xCPD · ETTh1 | MSE: 0.462 -> 0.445 | Improved |
| add learnable frequency partition (ablation) | DLinear+xCPD · ETTh1 | MSE: 0.448 -> 0.445 | Improved |
| add energy-based node grouping (ablation) | DLinear+xCPD · ETTh1 | MSE: 0.461 -> 0.445 | Improved |
| add spectral filters (ablation) | DLinear+xCPD · Traffic | MSE: 0.623 -> 0.606 | Improved |
| use spectral filters rather than Top-K/Random-K/RegionTop-K/TimeFilter (ablation) | DLinear+xCPD · ETTh1 | MSE: Top-K 0.464, TimeFilter 0.457 -> 0.445 | Improved |
| add expert diversity and balance regularizers (ablation) | DLinear+xCPD · Traffic | MSE: 0.609 -> 0.606 | Improved |
| add xCPD | DLinear · M4 average | SMAPE: 13.63 -> 12.43 | Improved |
Closest papers by meaning
- TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting (ICML 2025 · similarity 0.89)
- From Similarity to Superiority: Channel Clustering for Time Series Forecasting (NeurIPS 2024 · similarity 0.89)
- TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis (AAAI 2025 · similarity 0.89)
- Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series Forecasting (AAAI 2025 · similarity 0.88)
- CSformer: Combining Channel Independence and Mixing for Robust Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.87)
- HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.87)
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.
