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

arXiv: https://arxiv.org/abs/2401.02236 · HTML: https://mlsanity.com/paper/2401.02236/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures](https://mlsanity.com/paper/2207.01186/) (2022)
- [MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting](https://mlsanity.com/paper/2307.06736/) (2023)

## Built on by (most cited first, 7 of 7)

- [TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting](https://mlsanity.com/paper/2410.04442/) (2024)
- [TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation](https://mlsanity.com/paper/2503.07674/) (2025)
- [UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba](https://mlsanity.com/paper/2410.11278/) (2024)
- [ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting](https://mlsanity.com/paper/2509.06060/) (2025)
- [DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting](https://mlsanity.com/paper/2504.01531/) (2025)
- [D-CTNet: A Dual-Branch Channel-Temporal Forecasting Network with Frequency-Domain Correction](https://mlsanity.com/paper/2512.00925/) (2025)
- [SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies](https://mlsanity.com/paper/2605.14551/) (2026)

## Abstract (arXiv)

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.