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.

翻译：时间序列预测是各领域中的关键任务。由于趋势、季节性或不规则波动等因素，时间序列常呈现非平稳性。这会阻碍深层网络中特征的稳定传播，破坏特征分布，并增加学习数据分布变化的难度。因此，许多现有模型难以捕捉潜在模式，导致预测性能下降。本研究针对时间序列预测中的非平稳性挑战，提出名为U-Mixer的框架。通过结合Unet与Mixer结构，U-Mixer能分别有效捕捉不同块（patch）与通道间的局部时序依赖关系，避免通道间分布变化的干扰，并融合低层与高层特征以获取全面的数据表征。核心贡献在于提出一种新颖的平稳性修正方法——通过约束模型处理前后数据的平稳性差异，显式恢复原始数据分布，同时确保时序依赖关系的保留。在多种真实世界时间序列数据集上的大量实验表明，U-Mixer展现出有效性与鲁棒性，相较于最先进（SOTA）方法实现14.5%和7.7%的性能提升。