arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.08617cs.LGstat.ML
收藏

MTHetGNN:一个用于多变量时间序列预测的异构图嵌入框架

MTHetGNN: A Heterogeneous Graph Embedding Framework for Multivariate Time Series Forecasting

Chongqing University(重庆大学);Zhejiang University(浙江大学)

Yueyang Wang, Ziheng Duan, Yida Huang, Haoyan Xu, Jie Feng, Anni Ren

摘要:

多变量时间序列预测通过分析历史时间序列来预测未来趋势,可以有效地帮助决策。MTS中变量之间的复杂关系,包括静态、动态、可预测和潜在的关系,使得挖掘MTS的更多特征成为可能。复杂关系的建模不仅是刻画潜在依赖和建模时态依赖的必要条件,也给MTS预测任务带来了巨大的挑战。然而,现有的方法主要集中在建模MTS变量之间的某些关系。在本文中,我们提出了一种新的端到端深度学习模型,称为通过异构图神经网络进行多变量时间序列预测(MTHetGNN)。为了刻画变量之间的复杂关系,MTHetGNN设计了关系嵌入模块,将每个变量看作一个图节点,每种边表示一种特定的静态或动态关系。同时,时间嵌入模块引入时间序列的特征提取,其中涉及卷积神经网络(CNN)滤波器与不同的感知尺度。最后,采用异构图嵌入模块来处理两个模块生成的复杂结构信息。来自现实世界的三个基准数据集被用来评估所提出的MTHetGNN。综合实验表明,MTHetGNN在MTS预测任务中取得了较好的效果。

英文摘要:

Multivariate time series forecasting, which analyzes historical time series to predict future trends, can effectively help decision-making. Complex relations among variables in MTS, including static, dynamic, predictable, and latent relations, have made it possible to mining more features of MTS. Modeling complex relations are not only essential in characterizing latent dependency as well as modeling temporal dependence but also brings great challenges in the MTS forecasting task. However, existing methods mainly focus on modeling certain relations among MTS variables. In this paper, we propose a novel end-to-end deep learning model, termed Multivariate Time Series Forecasting via Heterogeneous Graph Neural Networks (MTHetGNN). To characterize complex relations among variables, a relation embedding module is designed in MTHetGNN, where each variable is regarded as a graph node, and each type of edge represents a specific static or dynamic relationship. Meanwhile, a temporal embedding module is introduced for time series features extraction, where involving convolutional neural network (CNN) filters with different perception scales. Finally, a heterogeneous graph embedding module is adopted to handle the complex structural information generated by the two modules. Three benchmark datasets from the real world are used to evaluate the proposed MTHetGNN. The comprehensive experiments show that MTHetGNN achieves state-of-the-art results in the MTS forecasting task.

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。

↑