arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.11285cs.LG
收藏

TimeSQL:通过多尺度分块与平滑二次损失改进多变量时间序列预测

TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss

College of Electrical Engineering, Sichuan University(四川大学电气工程学院);College of Architecture and Environment, Sichuan University(四川大学建筑与环境学院);State Grid Sichuan Electric Power Research Institute(国网四川省电力公司电力科学研究院);College of Computer Science, Sichuan University(四川大学计算机学院)

Site Mo, Haoxin Wang, Bixiong Li, Songhai Fan, Yuankai Wu, Xianggen Liu

AI总结:

提出TimeSQL框架,通过多尺度分块捕捉局部与长期相关性,并利用平滑二次损失(SQL)抑制噪声和异常值过拟合,在八个基准数据集上达到最先进性能,且其模块可作为即插即用技术增强其他模型。

摘要:

时间序列是一种特殊类型的序列数据,是在相等时间间隔下收集的实值随机变量序列。现实世界的多变量时间序列带有噪声,并包含复杂的局部和全局时间动态,使得在给定历史观测的情况下很难预测未来的时间序列。这项工作提出了一个简单有效的框架,称为 TimeSQL,它利用多尺度分块和平滑二次损失(SQL)来解决上述挑战。多尺度分块将时间序列转换为具有不同长度尺度的二维块,促进了对时间序列中局部性和长期相关性的感知。SQL 源自有理二次核,能够动态调整梯度以避免对噪声和异常值的过拟合。理论分析表明,在温和条件下,噪声对使用 SQL 的模型的影响始终小于使用 MSE 的模型。基于这两个模块,TimeSQL 在八个现实世界基准数据集上实现了新的最先进性能。进一步的消融研究表明,TimeSQL 中的关键模块还可以增强其他多变量时间序列预测模型的结果,作为即插即用的技术。

英文摘要:

Time series is a special type of sequence data, a sequence of real-valued random variables collected at even intervals of time. The real-world multivariate time series comes with noises and contains complicated local and global temporal dynamics, making it difficult to forecast the future time series given the historical observations. This work proposes a simple and effective framework, coined as TimeSQL, which leverages multi-scale patching and smooth quadratic loss (SQL) to tackle the above challenges. The multi-scale patching transforms the time series into two-dimensional patches with different length scales, facilitating the perception of both locality and long-term correlations in time series. SQL is derived from the rational quadratic kernel and can dynamically adjust the gradients to avoid overfitting to the noises and outliers. Theoretical analysis demonstrates that, under mild conditions, the effect of the noises on the model with SQL is always smaller than that with MSE. Based on the two modules, TimeSQL achieves new state-of-the-art performance on the eight real-world benchmark datasets. Further ablation studies indicate that the key modules in TimeSQL could also enhance the results of other models for multivariate time series forecasting, standing as plug-and-play techniques.

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。

↑