Skip to Content
You are currently on the new version of our website. Access the old version .
MathematicsMathematics
  • Article
  • Open Access

23 April 2026

21 Pages

PiTransformer: A Gated Patch-Wise Inverted Transformer for Stochastic Multivariate Time Series Forecasting

and
School of Electronic Information Engineering, Guiyang University, Guiyang 550005, China
*
Author to whom correspondence should be addressed.
This article belongs to the Section E: Applied Mathematics

Abstract

Multivariate time series forecasting presents a challenging problem in stochastic modeling, particularly under non-stationary conditions with low signal-to-noise ratios. While recent inverted architectures enhance cross-variable dependency modeling, the conventional point-wise inversion strategy often compromises local temporal patterns. To address this limitation, we propose PiTransformer, a gated patch-wise inverted framework for multivariate time series modeling. Specifically, a Patch-wise Inverted Embedding (PIE) mechanism is introduced to segment temporal sequences into regional patches prior to inversion, enabling the preservation of localized temporal structures. In addition, a Variable–Temporal Gating (VTG) module is incorporated to regulate feature interactions based on the information bottleneck principle, thereby suppressing spurious correlations in noisy environments. Empirical evaluations on diverse benchmarks—including financial and energy datasets—demonstrate that PiTransformer achieves consistent improvements in predictive accuracy and stability over competitive baselines. These results suggest that the proposed framework provides a robust and interpretable approach for modeling high-dimensional stochastic time series under non-stationary conditions.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.