GinAR：一种适用于变量缺失的端到端多变量时间序列预测模型
GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing
AI总结：
针对多变量时间序列中变量缺失导致STGNN依赖建模失真的问题，本文提出端到端GinAR模型，通过插值注意力恢复缺失变量并以自适应图卷积重建时空依赖，实验证明其优于11个SOTA基线且在90%变量缺失时仍可准确预测。
摘要：
多变量时间序列预测（MTSF）对于决策至关重要，其目标是基于从多个序列的历史观测中识别出的复杂关系，精确预测未来的数值或趋势。近年来，时空图神经网络（STGNN）凭借其在挖掘时空依赖关系方面的强大能力，逐渐成为MTSF模型的主流，但这类模型几乎都严重依赖历史数据完整性这一假设。在现实中，由于数据采集器故障、维修耗时等因素，要收集完整且不缺失任何变量的历史观测数据极具挑战。在这种情况下，STGNN只能利用一部分正常变量，并且容易出现错误的时空依赖建模问题，从而导致预测性能下降。为解决该问题，本文提出了一种新颖的图插值注意力递归网络（Graph Interpolation Attention Recursive Network，名为GinAR），用于在有限的已收集数据上精确建模时空依赖关系以进行预测。GinAR包含两个关键组件，即插值注意力和自适应图卷积，它们替代了简单递归单元中的全连接层，因此能够分别恢复所有缺失变量，并重建正确的时空依赖关系，以对多变量时间序列数据进行递归建模。在五个真实世界数据集上开展的大量实验表明，GinAR优于11个SOTA基线；即使在90%的变量缺失时，它仍能准确预测所有变量的未来数值。
英文摘要：
Multivariate time series forecasting (MTSF) is crucial for decision-making to precisely forecast the future values/trends, based on the complex relationships identified from historical observations of multiple sequences. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have gradually become the theme of MTSF model as their powerful capability in mining spatial-temporal dependencies, but almost of them heavily rely on the assumption of historical data integrity. In reality, due to factors such as data collector failures and time-consuming repairment, it is extremely challenging to collect the whole historical observations without missing any variable. In this case, STGNNs can only utilize a subset of normal variables and easily suffer from the incorrect spatial-temporal dependency modeling issue, resulting in the degradation of their forecasting performance. To address the problem, in this paper, we propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to precisely model the spatial-temporal dependencies over the limited collected data for forecasting. In GinAR, it consists of two key components, that is, interpolation attention and adaptive graph convolution to take place of the fully connected layer of simple recursive units, and thus are capable of recovering all missing variables and reconstructing the correct spatial-temporal dependencies for recursively modeling of multivariate time series data, respectively. Extensive experiments conducted on five real-world datasets demonstrate that GinAR outperforms 11 SOTA baselines, and even when 90% of variables are missing, it can still accurately predict the future values of all variables.
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。
