arXiv 2403.035082025-06-27cs.LG

EXPRTS：探索与探测时间序列预测模型的鲁棒性

EXPRTS: Exploring and Probing the Robustness of Time Series Forecasting Models

Aneo AS（Aneo公司）；Norwegian University of Science and Technology（挪威科学与技术大学）；University of California Santa Cruz（加州大学圣克鲁兹分校）；University of Bergen（卑尔根大学）

Håkon Hanisch Kjærnli, Lluis Mas-Ribas, Hans Jakob Håland, Vegard Sjåvik, Aida Ashrafi, Helge Langseth, Odd Erik Gundersen

备注：: under review

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对时间序列预测模型在分布外数据上缺乏鲁棒性且现有数据增强方法计算昂贵、不可解释的问题，提出结合时间序列分解与解析函数的可解释生成框架，并开发了可视化分析工具 EXPRTS，通过生成有意义的OOD时间序列有效提升模型鲁棒性。

摘要：

在将基于机器学习的时间序列预测模型部署到真实世界场景时，经常会遇到数据分布漂移的情况。这种漂移使预测模型暴露于分布外（OOD）数据，而机器学习模型在这些场景中缺乏鲁棒性。可以通过深度生成模型或遗传算法增强时间序列数据集来提高鲁棒性，但这些方法缺乏可解释性且计算成本高昂。在本研究中，我们开发了一个可解释且简单的生成时间序列框架。我们的方法将时间序列分解与解析函数相结合，能够生成特征同时匹配分布内和分布外数据的时间序列。这种方法允许用户以可解释的方式生成新的时间序列，从而用于增强数据集并提高预测鲁棒性。我们通过 EXPRTS 展示了该框架，这是一个为单变量时间序列预测模型和数据集设计的可视化分析工具。对数据分布、预测误差和单个时间序列实例的不同可视化，使用户能够探索时间序列数据集、应用变换，并评估预测模型在多种场景下的鲁棒性。我们展示了该框架如何生成有意义的 OOD 时间序列以提升模型鲁棒性，并通过三个用例和一项用户研究验证了 EXPRTS 的有效性和可用性。

英文摘要：

When deploying time series forecasting models based on machine learning to real world settings, one often encounter situations where the data distribution drifts. Such drifts expose the forecasting models to out-of-distribution (OOD) data, and machine learning models lack robustness in these settings. Robustness can be improved by using deep generative models or genetic algorithms to augment time series datasets, but these approaches lack interpretability and are computationally expensive. In this work, we develop an interpretable and simple framework for generating time series. Our method combines time-series decompositions with analytic functions, and is able to generate time series with characteristics matching both in- and out-of-distribution data. This approach allows users to generate new time series in an interpretable fashion, which can be used to augment the dataset and improve forecasting robustness. We demonstrate our framework through EXPRTS, a visual analytics tool designed for univariate time series forecasting models and datasets. Different visualizations of the data distribution, forecasting errors and single time series instances enable users to explore time series datasets, apply transformations, and evaluate forecasting model robustness across diverse scenarios. We show how our framework can generate meaningful OOD time series that improve model robustness, and we validate EXPRTS effectiveness and usability through three use-cases and a user study.

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。