Skip to main content
QUICK REVIEW

[论文解读] Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction

Huaxiu Yao, Xianfeng Tang|arXiv (Cornell University)|Mar 3, 2018
Traffic Prediction and Management Techniques参考文献 31被引用 78
一句话总结

STDN 引入一个流量门控机制用于动态空间相似性,以及一个周期性偏移注意力机制用于长期周期性时间偏移,从而提升交通预测。

ABSTRACT

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.

研究动机与目标

  • 推动对随时间改变的交通数据中的动态空间依赖关系建模。
  • 解决长期时序模式中非严格的日/周周期性以及时间偏移问题。
  • 提出将时空动态与自适应注意力机制结合的统一架构。
  • 在大规模真实世界数据集(纽约市出租车和共享单车数据)上展示有效性。

提出的方法

  • 流量门控机制(FGM),通过交通流数据学习动态空间相似性,并对空间传播进行门控调制。
  • 本地时空网络(LSTN),使用局部卷积神经网络提取空间特征,并使用长短期记忆网络捕捉短期时序动态。
  • 周期性偏移注意力机制(PSAM),通过跨日/跨周的时间偏移捕捉长期周期性。
  • 将短期(LSTN)和长期周期性表示联合训练为对起始和结束交通量的统一预测。
  • 使用共享表示和联合损失函数进行起始量和结束量的多任务预测。

实验结果

研究问题

  • RQ1如何有效建模区域间的动态空间相似性以用于交通预测?
  • RQ2当周期性随时间改变时,能否捕捉交通时间序列中的长期周期性?
  • RQ3联合建模起始量和结束量是否能提升预测性能?
  • RQ4将基于流的空间门控和周期性偏移注意力引入对预测准确性有何影响?

主要发现

数据集方法起始 RMSE起始 MAPE结束 RMSE结束 MAPE
NYC-TaxiSTDN24.10 ± 0.2516.30% ± 0.2319.05 ± 0.3116.25% ± 0.26
  • STDN 在 NYC-Taxi 和 NYC-Bike 数据集上在 RMSE 和 MAPE 指标持续优于基线。
  • 单独的流量门控在空间依赖建模上优于静态或基于特征的流表示。
  • 周期性偏移注意力能有效处理长期周期性中的时间偏移,提升预测。
  • STDN 超越 ConvLSTM、ST-ResNet、DMVST-Net 及其他前沿模型,验证了动态时空方法的有效性。
  • 使用共享表示对起始量和结束量进行联合建模比分开建模获得更好的性能。

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。