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 2401.08119cs.LG
收藏

SpecSTG:一种用于概率性时空交通预测的快速谱扩散框架

SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecasting

The University of Sydney(悉尼大学);Riken AIP(理化学研究所先进智能项目)

Lequan Lin, Dai Shi, Andi Han, Junbin Gao

AI总结:

SpecSTG提出一种快速谱扩散框架,通过傅里叶表示和快速谱图卷积利用空间依赖,在交通预测的点估计和不确定性量化上均优于现有方法,且训练验证速度提升至3.33倍。

摘要:

交通预测作为时空图(STG)学习的一项关键应用,传统上依赖确定性模型进行精确的点估计。然而,这些模型难以量化未来不确定性。近年来,许多概率方法,尤其是扩散模型的变体,被提出以填补这一空白。但现有的扩散方法在生成未来时间序列时通常单独处理各个传感器,导致概率学习过程中空间信息利用不足。在本工作中,我们提出SpecSTG,一种新颖的谱扩散框架,以更好地利用交通数据中固有的空间依赖性和系统性模式。具体而言,我们的方法生成未来时间序列的傅里叶表示,将学习过程转换到富含空间信息的谱域中。此外,我们的方法引入了一种专为傅里叶输入设计的快速谱图卷积,减轻了现有模型的计算负担。与最先进方法相比,SpecSTG在点估计上实现了高达8%的改进,在量化未来不确定性上实现了高达0.78%的改进。此外,SpecSTG的训练和验证速度是现有最高效的STG预测扩散方法的3.33倍。SpecSTG的源代码可在https://anonymous.4open.science/r/SpecSTG获取。

英文摘要:

Traffic forecasting, a crucial application of spatio-temporal graph (STG) learning, has traditionally relied on deterministic models for accurate point estimations. Yet, these models fall short of quantifying future uncertainties. Recently, many probabilistic methods, especially variants of diffusion models, have been proposed to fill this gap. However, existing diffusion methods typically deal with individual sensors separately when generating future time series, resulting in limited usage of spatial information in the probabilistic learning process. In this work, we propose SpecSTG, a novel spectral diffusion framework, to better leverage spatial dependencies and systematic patterns inherent in traffic data. More specifically, our method generates the Fourier representation of future time series, transforming the learning process into the spectral domain enriched with spatial information. Additionally, our approach incorporates a fast spectral graph convolution designed for Fourier input, alleviating the computational burden associated with existing models. Compared with state-of-the-arts, SpecSTG achieves up to 8% improvements on point estimations and up to 0.78% improvements on quantifying future uncertainties. Furthermore, SpecSTG's training and validation speed is 3.33X of the most efficient existing diffusion method for STG forecasting. The source code for SpecSTG is available at https://anonymous.4open.science/r/SpecSTG.

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。

↑