arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.02403cs.LGcs.AI
收藏

基于改进深度学习的非平稳时间序列自适应预测

Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series

Google Cloud AI(谷歌云人工智能)

Sercan O. Arik, Nathanael C. Yoder, Tomas Pfister

摘要:

真实世界的时间序列数据集经常违反标准监督学习预测的假设-它们的分布随着时间的推移而演变,使得传统的训练和模型选择过程次优。在本文中,我们提出了一种新的方法,自适应预测(SAF),修改训练的时间序列预测模型,以提高其性能的预测任务与这种非平稳的时间序列数据。SAF在基于“回溯”的预测之前集成了一个自适应阶段,即在时间上向后预测掩蔽的输入。这是一种测试时训练的形式,在执行预测任务之前在测试样本上创建自监督学习问题。通过这种方式,我们的方法使编码表示能够有效地适应不断变化的分布,从而获得更好的泛化能力。SAF可以与任何基于规范编码器-解码器的时间序列架构集成,例如递归神经网络或基于注意力的架构。在时间序列数据众所周知是非平稳的领域(如医疗保健和金融)的合成和真实数据集上,我们证明了SAF在提高预测准确性方面的显著优势。

英文摘要:

Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal. In this paper, we propose a novel method, Self-Adaptive Forecasting (SAF), to modify the training of time-series forecasting models to improve their performance on forecasting tasks with such non-stationary time-series data. SAF integrates a self-adaptation stage prior to forecasting based on `backcasting', i.e. predicting masked inputs backward in time. This is a form of test-time training that creates a self-supervised learning problem on test samples before performing the prediction task. In this way, our method enables efficient adaptation of encoded representations to evolving distributions, leading to superior generalization. SAF can be integrated with any canonical encoder-decoder based time-series architecture such as recurrent neural networks or attention-based architectures. On synthetic and real-world datasets in domains where time-series data are known to be notoriously non-stationary, such as healthcare and finance, we demonstrate a significant benefit of SAF in improving forecasting accuracy.

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。

↑