U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting

TL;DR

U-Mixer is a novel deep learning framework that combines Unet and Mixer architectures with a stationarity correction method to improve time series forecasting by effectively handling non-stationarity and capturing temporal dependencies.

Contribution

The paper introduces U-Mixer, a new model that explicitly corrects for non-stationarity in time series, enhancing forecasting accuracy over existing methods.

Findings

Achieves 14.5% improvement over SOTA methods.

Demonstrates robustness across various datasets.

Effectively captures local temporal dependencies.

Abstract

Time series forecasting is a crucial task in various domains. Caused by factors such as trends, seasonality, or irregular fluctuations, time series often exhibits non-stationary. It obstructs stable feature propagation through deep layers, disrupts feature distributions, and complicates learning data distribution changes. As a result, many existing models struggle to capture the underlying patterns, leading to degraded forecasting performance. In this study, we tackle the challenge of non-stationarity in time series forecasting with our proposed framework called U-Mixer. By combining Unet and Mixer, U-Mixer effectively captures local temporal dependencies between different patches and channels separately to avoid the influence of distribution variations among channels, and merge low- and high-levels features to obtain comprehensive data representations. The key contribution is a novel stationarity correction method, explicitly restoring data distribution by constraining the difference in stationarity between the data before and after model processing to restore the non-stationarity information, while ensuring the temporal dependencies are preserved. Through extensive experiments on various real-world time series datasets, U-Mixer demonstrates its effectiveness and robustness, and achieves 14.5\% and 7.7\% improvements over state-of-the-art (SOTA) methods.