arXiv 2406.122822024-06-18cs.LG

SAGDFN：面向多变量时间序列预测的可扩展自适应图扩散预测网络

SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting

Nanyang Technological University（南洋理工大学）；Harbin Institute of Technology(Shenzhen)（哈尔滨工业大学（深圳））；NCS Pte Ltd（NCS私人有限公司）；DAMO Academy, Alibaba group（阿里巴巴达摩院）

Yue Jiang, Xiucheng Li, Yile Chen, Shuai Liu, Weilong Kong, Antonis F. Lentzakis, Gao Cong

备注：: Accepted at ICDE 2024

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有时空图神经网络在大规模多变量时间序列预测中可扩展性差、性能受限的问题，提出无需空间先验知识的SAGDFN，可适配数千节点数据集，在大规模数据集上性能显著优于现有最优方法。

摘要：

时间序列预测对我们的日常活动至关重要，而对多条时间序列间的复杂关联与共享模式进行精准建模，是提升预测性能的关键。时空图神经网络（STGNNs）因具备建模底层复杂时空依赖关系的能力，被广泛应用于多变量时间序列预测任务，且在多个真实数据集上取得了可观的性能表现。但现有研究受时空图神经网络高昂的计算与内存成本限制，主要针对仅包含数百个传感器的数据集展开；当应用于更大规模的数据集时，这类方法无法捕捉底层复杂的空间依赖关系，可扩展性与性能均表现有限。为此，我们提出了可扩展自适应图扩散预测网络（SAGDFN），用于捕捉大规模多变量时间序列的复杂时空关联，进而在多变量时间序列预测任务中实现优异性能。所提出的SAGDFN可扩展至包含数千个节点的数据集，且无需空间关联的先验知识。大量实验表明，SAGDFN在一个含207个节点的真实数据集上取得了与当前最优基线方法相当的性能，在三个含2000个节点的真实数据集上则以显著优势优于所有当前最优基线方法。

英文摘要：

Time series forecasting is essential for our daily activities and precise modeling of the complex correlations and shared patterns among multiple time series is essential for improving forecasting performance. Spatial-Temporal Graph Neural Networks (STGNNs) are widely used in multivariate time series forecasting tasks and have achieved promising performance on multiple real-world datasets for their ability to model the underlying complex spatial and temporal dependencies. However, existing studies have mainly focused on datasets comprising only a few hundred sensors due to the heavy computational cost and memory cost of spatial-temporal GNNs. When applied to larger datasets, these methods fail to capture the underlying complex spatial dependencies and exhibit limited scalability and performance. To this end, we present a Scalable Adaptive Graph Diffusion Forecasting Network (SAGDFN) to capture complex spatial-temporal correlation for large-scale multivariate time series and thereby, leading to exceptional performance in multivariate time series forecasting tasks. The proposed SAGDFN is scalable to datasets of thousands of nodes without the need of prior knowledge of spatial correlation. Extensive experiments demonstrate that SAGDFN achieves comparable performance with state-of-the-art baselines on one real-world dataset of 207 nodes and outperforms all state-of-the-art baselines by a significant margin on three real-world datasets of 2000 nodes.

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。