arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.10909cs.LGcs.AI
收藏

用于交通预测的图神经粗糙微分方程

Graph Neural Rough Differential Equations for Traffic Forecasting

Yonsei University(延世大学)

Jeongwhan Choi, Noseong Park

AI总结:

本文提出 STG-NRDE 框架,通过两个分别处理时间与空间信息的神经粗糙微分方程建模交通时空数据,并在 6 个数据集上超越 27 个基线。

摘要:

交通预测是机器学习领域最受欢迎的时空任务之一。该领域中一种普遍采用的方法是将图卷积网络与循环神经网络相结合,以进行时空处理。相关竞争十分激烈,许多新颖方法已被提出。在本文中,我们提出了时空图神经粗糙微分方程(STG-NRDE)方法。神经粗糙微分方程(NRDE)是处理时间序列数据的突破性概念。其主要思想是使用对数签名变换,将一个时间序列样本转换为相对更短的特征向量序列。我们扩展了这一概念,并设计了两个 NRDE:一个用于时间处理,另一个用于空间处理。随后,我们将二者组合到一个统一框架中。我们在 6 个基准数据集和 27 个基线方法上进行了实验。STG-NRDE 在所有情况下均取得最佳准确率,并且以不可忽视的幅度优于全部 27 个基线方法。

英文摘要:

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present the method of spatio-temporal graph neural rough differential equation (STG-NRDE). Neural rough differential equations (NRDEs) are a breakthrough concept for processing time-series data. Their main concept is to use the log-signature transform to convert a time-series sample into a relatively shorter series of feature vectors. We extend the concept and design two NRDEs: one for the temporal processing and the other for the spatial processing. After that, we combine them into a single framework. We conduct experiments with 6 benchmark datasets and 27 baselines. STG-NRDE shows the best accuracy in all cases, outperforming all those 27 baselines by non-trivial margins.

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。

↑