DeepGate: Global-local decomposition for multivariate time series modeling

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.

Automated summary

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.