Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Xiang, Li, Xuemei, Fang, Lexin, Zhao, Tianlong, Zhang, Caiming
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2401.02236
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913186011152384
author Ma, Xiang
Li, Xuemei
Fang, Lexin
Zhao, Tianlong
Zhang, Caiming
author_facet Ma, Xiang
Li, Xuemei
Fang, Lexin
Zhao, Tianlong
Zhang, Caiming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02236
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting
Ma, Xiang
Li, Xuemei
Fang, Lexin
Zhao, Tianlong
Zhang, Caiming
Machine Learning
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.
title U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2401.02236