arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.09620cs.LGstat.ML
收藏

在时间序列预测中你可能不需要顺序

You May Not Need Order in Time Series Forecasting

UC Santa Barbara(加州大学圣巴巴拉分校);Brown University(布朗大学);UC Los Angeles(加州大学洛杉矶分校);Columbia University(哥伦比亚大学)

Yunkai Zhang, Qiao Jiang, Shurui Li, Xiaoyong Jin, Xueying Ma, Xifeng Yan

摘要:

有限数据的时间序列预测是一项具有挑战性的关键任务。虽然Transformers在时间序列预测中取得了优异的性能,但由于大量的可训练参数,它们通常需要许多训练样本。在本文中,我们提出了一种Transformers的训练技术,通过随机采样准备训练窗口。由于输入时间步长不需要是连续的,因此不同样本的数量从线性增加到组合地增加。通过打破时间顺序,这种技术还有助于Transformers以更细的粒度捕获时间步长之间的依赖关系。与现实世界数据集上的最先进技术相比,我们取得了具有竞争力的结果。

英文摘要:

Time series forecasting with limited data is a challenging yet critical task. While transformers have achieved outstanding performances in time series forecasting, they often require many training samples due to the large number of trainable parameters. In this paper, we propose a training technique for transformers that prepares the training windows through random sampling. As input time steps need not be consecutive, the number of distinct samples increases from linearly to combinatorially many. By breaking the temporal order, this technique also helps transformers to capture dependencies among time steps in finer granularity. We achieve competitive results compared to the state-of-the-art on real-world datasets.

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。

↑