用于时间序列分析的多尺度分解 MLP-Mixer
A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis
AI总结：
针对时间序列多尺度变化与分解完整性问题，提出 MSD-Mixer，通过多尺度时间分块与 MLP 捕捉块内外变化及通道相关性，并设计残差约束损失函数，在五项任务上显著优于现有算法。
摘要：
时间序列数据，包括单变量和多变量数据，具有独特的组成和复杂的多尺度时间变化。它们通常需要特别考虑分解和多尺度建模来进行分析。现有的深度学习方法最适合单变量时间序列，且未充分考虑子序列建模和分解完整性。为应对这些挑战，我们提出了 MSD-Mixer，即多尺度分解 MLP-Mixer，它在其不同层中学习显式分解和表示输入时间序列。为处理多尺度时间模式和多元依赖关系，我们提出了一种新颖的时间分块方法，将时间序列建模为多尺度块，并采用 MLP 捕捉块内和块间变化以及通道相关性。此外，我们提出了一种新颖的损失函数，以约束分解残差的均值和自相关性，从而获得更好的分解完整性。通过对各种真实世界数据集进行五项常见时间序列分析任务的广泛实验，我们证明 MSD-Mixer 以更高效率持续且显著地优于其他最先进算法。
英文摘要：
Time series data, including univariate and multivariate ones, are characterized by unique composition and complex multi-scale temporal variations. They often require special consideration of decomposition and multi-scale modeling to analyze. Existing deep learning methods on this best fit to univariate time series only, and have not sufficiently considered sub-series modeling and decomposition completeness. To address these challenges, we propose MSD-Mixer, a Multi-Scale Decomposition MLP-Mixer, which learns to explicitly decompose and represent the input time series in its different layers. To handle the multi-scale temporal patterns and multivariate dependencies, we propose a novel temporal patching approach to model the time series as multi-scale patches, and employ MLPs to capture intra- and inter-patch variations and channel-wise correlations. In addition, we propose a novel loss function to constrain both the mean and the autocorrelation of the decomposition residual for better decomposition completeness. Through extensive experiments on various real-world datasets for five common time series analysis tasks, we demonstrate that MSD-Mixer consistently and significantly outperforms other state-of-the-art algorithms with better efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
