Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Jung Min Choi, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme• 2026

Related benchmarks

TaskDatasetResultRank
Multivariate ForecastingETTh1
MSE0.361
830
Time Series ForecastingETTh2
MSE0.267
796
Multivariate Time-series ForecastingETTm1
MSE0.306
686
Multivariate Time-series ForecastingETTm2
MSE0.166
539
Time Series ForecastingWeather
MSE0.14
497
Multivariate Time-series ForecastingWeather
MSE0.239
409
Multivariate Time-series ForecastingTraffic
MSE0.442
310
Time Series ForecastingETTm2
MSE0.162
300
Time Series ForecastingElectricity
MSE0.128
237
Multivariate Time-series ForecastingETTh2
MSE0.361
198
Showing 10 of 18 rows

Other info

Follow for update