NPMixer: Hierarchical Neighboring Patch Mixing for Time Series Forecasting
About
Multivariate time series forecasting remains a challenge due to the complexity of local temporal dynamics and global dependencies across multiple variables. In this paper, we propose \textbf{N}eighboring \textbf{P}atching \textbf{Mixer} (\textbf{NPMixer}), a hierarchical architecture featuring a Learnable Stationary Wavelet Transform that adaptively learns filter coefficients to decompose signals into trend and detail components in a data-dependent manner. Our framework introduces a Neighboring Mixer Block that captures local temporal dynamics through a series of hierarchical MLP layers operating on non-overlapping patches. Specifically, the mixer block utilizes MLPs to learn temporal patterns within and across these patches, expanding the receptive field to capture multi-scale dependencies. A Channel-Mixing Encoder is applied to high-frequency components to learn channel correlations while preserving the stability of the underlying global trend. Extensive experiments on seven benchmark datasets demonstrate that NPMixer consistently outperforms state-of-the-art models, achieving better performance in 20 out of 28 ($71.4\%$) evaluated experimental setups for MSE.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Multivariate Forecasting | ETTh1 | MSE0.361 | 830 | |
| Time Series Forecasting | ETTh2 | MSE0.267 | 796 | |
| Multivariate Time-series Forecasting | ETTm1 | MSE0.306 | 686 | |
| Multivariate Time-series Forecasting | ETTm2 | MSE0.166 | 539 | |
| Time Series Forecasting | Weather | MSE0.14 | 497 | |
| Multivariate Time-series Forecasting | Weather | MSE0.239 | 409 | |
| Multivariate Time-series Forecasting | Traffic | MSE0.442 | 310 | |
| Time Series Forecasting | ETTm2 | MSE0.162 | 300 | |
| Time Series Forecasting | Electricity | MSE0.128 | 237 | |
| Multivariate Time-series Forecasting | ETTh2 | MSE0.361 | 198 |