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 1803.01254cs.LG
收藏

时空相似性再探:一个用于流量预测的深度学习框架

Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction

Pennsylvania State University(宾夕法尼亚州立大学)

Huaxiu Yao, Xianfeng Tang, Hua Wei, Guanjie Zheng, Zhenhui Li

摘要:

由于大规模交通数据的可用性及其在现实世界中的重要性,交通预测在人工智能研究领域引起了越来越多的关注。例如,准确的出租车需求预测可以帮助出租车公司预先分配出租车。交通预测的关键挑战在于如何对复杂的空间相关性和时间动态性进行建模。虽然这两个因素都已被考虑在建模中,现有的作品作出强有力的假设空间依赖性和时间动态,即,空间依赖性在时间上是稳定的,而时间动态是严格周期性的。然而,在实践中,空间依赖性可以是动态的(即,随时间变化),并且时间动态从一个周期到另一个周期可能具有一些扰动。在本文中,我们做了两个重要的观察:(1)位置之间的空间依赖是动态的;(2)时间依赖遵循每日和每周的模式,但它不是严格的周期性的动态时间转移。为了解决这两个问题,我们提出了一种新的时空动态网络(STDN),其中引入了流门机制来学习位置之间的动态相似性,并设计了一个周期性转移的注意力机制来处理长期的周期性时间转移。据我们所知,这是在一个统一的框架内处理这两个问题的第一项工作。在真实交通数据集上的实验结果验证了该方法的有效性。

英文摘要:

Traffic prediction has drawn increasing attention in AI research field due to the increasing availability of large-scale traffic data and its importance in the real world. For example, an accurate taxi demand prediction can assist taxi companies in pre-allocating taxis. The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice, the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. To address these two issues, we propose a novel Spatial-Temporal Dynamic Network (STDN), in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting. To the best of our knowledge, this is the first work that tackles both issues in a unified framework. Our experimental results on real-world traffic datasets verify the effectiveness of the proposed method.

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。

↑