arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2311.04522cs.LG
收藏

基于分解和神经常微分方程的长期时间序列预测

Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equations

Yonsei University(延世大学)

Seonkyu Lim, Jaehyeon Park, Seojin Kim, Hyowon Wi, Haksoo Lim, Jinsung Jeon, Jeongwhan Choi, Noseong Park

AI总结:

针对线性LTSF模型过于简单的问题,提出LTSF-DNODE,结合线性常微分方程与时间序列分解,在多个真实数据集上超越基线,并探讨了NODE框架中正则化的影响。

摘要:

长期时间序列预测(LTSF)是一项具有挑战性的任务,已在金融投资、医疗保健、交通和天气预报等多个领域得到研究。近年来,基于线性的LTSF模型表现出更好的性能,指出了基于Transformer的方法导致时间信息丢失的问题。然而,基于线性的方法也存在局限性,即模型过于简单,无法全面利用数据集的特征。为解决这些局限性,我们提出了LTSF-DNODE,该模型基于线性常微分方程(ODEs)并根据数据统计特征应用时间序列分解方法。我们展示了LTSF-DNODE在各种真实世界数据集上优于基线模型。此外,对于每个数据集,我们探讨了神经常微分方程(NODE)框架中正则化的影响。

英文摘要:

Long-term time series forecasting (LTSF) is a challenging task that has been investigated in various domains such as finance investment, health care, traffic, and weather forecasting. In recent years, Linear-based LTSF models showed better performance, pointing out the problem of Transformer-based approaches causing temporal information loss. However, Linear-based approach has also limitations that the model is too simple to comprehensively exploit the characteristics of the dataset. To solve these limitations, we propose LTSF-DNODE, which applies a model based on linear ordinary differential equations (ODEs) and a time series decomposition method according to data statistical characteristics. We show that LTSF-DNODE outperforms the baselines on various real-world datasets. In addition, for each dataset, we explore the impacts of regularization in the neural ordinary differential equation (NODE) framework.

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。

↑