期刊
INFORMATION SCIENCES
卷 590, 期 -, 页码 158-178出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2022.01.015
关键词
Time series analysis; Global-local decomposition; Multivariate time series; Multi-step forecasting; Interpretable neural networks
资金
- msit (ministry of science and ict), Korea [IITP-2017-0-00477]
In this study, we propose DeepGate, a time series forecasting framework based on explicit global-local decomposition. By separating the decomposition and prediction modules, DeepGate is able to generate interpretable global series while improving forecasting performance. Experimental results demonstrate that DeepGate outperforms baseline models in time series forecasting tasks.
In multivariate time series, a substantial amount of variables exhibit common dynamics stemming from a small number of global factors. Recent studies have shown that the shared information from global components can enhance the forecasting performance of time series. However, existing global-local approaches treat the global factors as additional hidden states inside the model without providing global series for downstream analysis. In this study, we propose DeepGate, a novel time series forecasting framework based on the explicit global-local decomposition. To retain the global and local series property, we have built decomposition and prediction modules separately. In this way, DeepGate can produce interpretable global series for further tasks while improving forecasting performance with the aid of global and local series. In addition, to alleviate the discrepancy between the training and testing steps, we employ a denoising training technique for multi-step forecasting problems. In numerous experiments on real-world benchmarks for time series forecasting, DeepGate outperforms the baselines including existing global-local models. In particular, the experimental results on synthetic tasks demonstrate that our model can effectively extract underlying global series. (C) 2022 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据