arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.16178cs.LGstat.ML
收藏

SWIFT:基于小波分解的子序列映射提升时间序列预测

SWIFT: Mapping Sub-series with Wavelet Decomposition Improves Time Series Forecasting

South China University of Technology, Guangzhou, China(华南理工大学)

Wenxuan Xie, Fanpu Cao

AI总结:

SWIFT通过小波分解和轻量级结构提升长期时间序列预测的效率与性能。

摘要:

在最近的时间序列预测研究中,Transformer和大型语言模型由于其在序列建模中的强大能力而受到广泛关注。然而,在实际部署中,时间序列预测往往需要在资源受限的环境中运行,例如边缘设备,这些设备无法处理大型模型的计算开销。为了解决此类场景,一些轻量级模型已被提出,但它们在非平稳序列上表现较差。在本文中,我们提出了SWIFT,一种轻量级模型,不仅强大,而且在长期时间序列预测(LTSF)的部署和推理中具有高效性。我们的模型基于三个关键点:(i)利用小波变换对时间序列进行无损下采样。(ii)通过可学习的滤波器实现跨频带信息融合。(iii)仅使用一个共享的线性层或一个浅层MLP对子序列进行映射。我们进行了全面的实验,结果表明,SWIFT在多个数据集上实现了最先进的性能,为边缘计算和该任务的部署提供了一种有前途的方法。此外,值得注意的是,SWIFT-Linear的参数数量仅为单层线性模型在时域预测中的25%。我们的代码可在https://github.com/LancelotXWX/SWIFT上获得。

英文摘要:

In recent work on time-series prediction, Transformers and even large language models have garnered significant attention due to their strong capabilities in sequence modeling. However, in practical deployments, time-series prediction often requires operation in resource-constrained environments, such as edge devices, which are unable to handle the computational overhead of large models. To address such scenarios, some lightweight models have been proposed, but they exhibit poor performance on non-stationary sequences. In this paper, we propose $\textit{SWIFT}$, a lightweight model that is not only powerful, but also efficient in deployment and inference for Long-term Time Series Forecasting (LTSF). Our model is based on three key points: (i) Utilizing wavelet transform to perform lossless downsampling of time series. (ii) Achieving cross-band information fusion with a learnable filter. (iii) Using only one shared linear layer or one shallow MLP for sub-series' mapping. We conduct comprehensive experiments, and the results show that $\textit{SWIFT}$ achieves state-of-the-art (SOTA) performance on multiple datasets, offering a promising method for edge computing and deployment in this task. Moreover, it is noteworthy that the number of parameters in $\textit{SWIFT-Linear}$ is only 25\% of what it would be with a single-layer linear model for time-domain prediction. Our code is available at https://github.com/LancelotXWX/SWIFT.

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。

↑