arXiv 2402.151342024-02-23cs.LGcs.AI

用于多元时间序列预测的深度耦合网络

Deep Coupling Network For Multivariate Time Series Forecasting

School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；School of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）；School of Computer Science and Information Engineering, HeFei University of Technology（合肥工业大学计算机与信息工程学院）

Kun Yi, Qi Zhang, Hui He, Kaize Shi, Liang Hu, Ning An, Zhendong Niu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文从互信息视角提出深度耦合网络DeepCN，通过同时建模多阶序列内与序列间耦合关系，提升多元时间序列预测精度，并在七个数据集上验证其优越性。

摘要：

多元时间序列（MTS）预测在许多现实应用中至关重要。为了实现准确的MTS预测，必须同时考虑时间序列数据内部的序列内关系以及序列间关系。然而，以往的工作通常分别建模序列内和序列间关系，并且忽视了时间序列数据内部及之间存在的多阶交互，这会严重降低预测精度。在本文中，我们从互信息的角度重新审视序列内和序列间关系，并据此构建了一个综合关系学习机制，专门用于同时捕获复杂的多阶序列内和序列间耦合。基于该机制，我们提出了一种新颖的用于MTS预测的深度耦合网络，命名为DeepCN，它包含一个耦合机制，专门用于同时显式探索时间序列数据之间的多阶序列内和序列间关系；一个耦合变量表示模块，旨在编码多样的变量模式；以及一个推理模块，通过一步前向过程促进预测。在七个真实世界数据集上进行的大量实验表明，与最先进的基线方法相比，我们提出的DeepCN取得了优越的性能。

英文摘要：

Multivariate time series (MTS) forecasting is crucial in many real-world applications. To achieve accurate MTS forecasting, it is essential to simultaneously consider both intra- and inter-series relationships among time series data. However, previous work has typically modeled intra- and inter-series relationships separately and has disregarded multi-order interactions present within and between time series data, which can seriously degrade forecasting accuracy. In this paper, we reexamine intra- and inter-series relationships from the perspective of mutual information and accordingly construct a comprehensive relationship learning mechanism tailored to simultaneously capture the intricate multi-order intra- and inter-series couplings. Based on the mechanism, we propose a novel deep coupling network for MTS forecasting, named DeepCN, which consists of a coupling mechanism dedicated to explicitly exploring the multi-order intra- and inter-series relationships among time series data concurrently, a coupled variable representation module aimed at encoding diverse variable patterns, and an inference module facilitating predictions through one forward step. Extensive experiments conducted on seven real-world datasets demonstrate that our proposed DeepCN achieves superior performance compared with the state-of-the-art baselines.

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。