论文标题
可解释的张力神经普通微分方程前列表时间序列预测
Explainable Tensorized Neural Ordinary Differential Equations forArbitrary-step Time Series Prediction
论文作者
论文摘要
我们提出了一个连续的神经网络体系结构，称为在任意时间点的多步骤时间序列预测的可解释的张力神经常规微分方程（ETN-ODE）。与现有方法不同，该方法主要处理单步预测的多步预测或多变量时间序列的单变量时间序列，ETN-ODE可以为任意步骤预测的多变量时间序列建模。此外，W.R.T.享有双重关注。时间关注和可变的关注，能够为数据提供可解释的见解。具体而言，ETN-ODE结合了可解释的封闭的复发单元（张力GRU或TGRU）与普通微分方程（ODE）。潜在状态的导数通过神经网络进行了参数化。这种连续的ode网络可以在任意时间点上进行多步预测。我们对五个不同的多步预测任务和一个任意步骤的预测任务进行定量和定性地证明ETN-ODE的有效性和解释性。广泛的实验表明，ETN-ODE可以在任意时间点上导致准确的预测，同时在标准多步骤时间序列预测中对基线方法的最佳性能。
We propose a continuous neural network architecture, termed Explainable Tensorized Neural Ordinary Differential Equations (ETN-ODE), for multi-step time series prediction at arbitrary time points. Unlike the existing approaches, which mainly handle univariate time series for multi-step prediction or multivariate time series for single-step prediction, ETN-ODE could model multivariate time series for arbitrary-step prediction. In addition, it enjoys a tandem attention, w.r.t. temporal attention and variable attention, being able to provide explainable insights into the data. Specifically, ETN-ODE combines an explainable Tensorized Gated Recurrent Unit (Tensorized GRU or TGRU) with Ordinary Differential Equations (ODE). The derivative of the latent states is parameterized with a neural network. This continuous-time ODE network enables a multi-step prediction at arbitrary time points. We quantitatively and qualitatively demonstrate the effectiveness and the interpretability of ETN-ODE on five different multi-step prediction tasks and one arbitrary-step prediction task. Extensive experiments show that ETN-ODE can lead to accurate predictions at arbitrary time points while attaining best performance against the baseline methods in standard multi-step time series prediction.
