Discrete Graph Structure Learning for Forecasting Multiple Time Series
Discrete Graph Structure Learning for Forecasting Multiple Time Series
复制标题
DOI：
--
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Chao Shang;Jie Chen;J. Bi
中科院分区：
文献类型：
--
作者：
Chao Shang;Jie Chen;J. Bi
时间序列预测是统计学、经济学和计算机科学中一个被广泛研究的课题。探索多变量时间序列中变量之间的相关性和因果关系显示出提高时间序列模型性能的希望。当使用深度神经网络作为预测模型时，我们假设利用多个(多变量)时间序列之间的成对信息也可以改善它们的预测。如果已知一种显式的图结构，则图神经网络(GNN)已被证明是开发该结构的有力工具。在这项工作中，我们建议在图未知的情况下与GNN同时学习结构。我们将问题归结为通过优化图分布上的平均性能来学习概率图模型。该分布通过神经网络进行参数化，从而可以通过重新参数化对离散图形进行差分采样。实验表明，我们的方法比最近提出的用于图结构学习的两层学习方法更简单、更有效、性能更好，也比基于深度或非深度学习的各种预测模型以及基于图或非图的预测模型更好。
Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.