Skip to main content
QUICK REVIEW

[论文解读] STG-GAN: A spatiotemporal graph generative adversarial networks for short-term passenger flow prediction in urban rail transit systems

Jinlei Zhang, Hua Li|arXiv (Cornell University)|Feb 10, 2022
Traffic Prediction and Management Techniques被引用 4
一句话总结

本文提出STG-GAN,一种新颖的时空图生成对抗网络,通过对抗性训练联合建模空间与时间依赖性,提升城市轨道交通的短时客流预测性能。该模型在轻量级生成器中结合门控时间卷积与参数共享图卷积,搭配空间与时间判别器,实现在真实北京地铁数据上的高精度、高效率与低内存占用。

ABSTRACT

Short-term passenger flow prediction is an important but challenging task for better managing urban rail transit (URT) systems. Some emerging deep learning models provide good insights to improve short-term prediction accuracy. However, there exist many complex spatiotemporal dependencies in URT systems. Most previous methods only consider the absolute error between ground truth and predictions as the optimization objective, which fails to account for spatial and temporal constraints on the predictions. Furthermore, a large number of existing prediction models introduce complex neural network layers to improve accuracy while ignoring their training efficiency and memory occupancy, decreasing the chances to be applied to the real world. To overcome these limitations, we propose a novel deep learning-based spatiotemporal graph generative adversarial network (STG-GAN) model with higher prediction accuracy, higher efficiency, and lower memory occupancy to predict short-term passenger flows of the URT network. Our model consists of two major parts, which are optimized in an adversarial learning manner: (1) a generator network including gated temporal conventional networks (TCN) and weight sharing graph convolution networks (GCN) to capture structural spatiotemporal dependencies and generate predictions with a relatively small computational burden; (2) a discriminator network including a spatial discriminator and a temporal discriminator to enhance the spatial and temporal constraints of the predictions. The STG-GAN is evaluated on two large-scale real-world datasets from Beijing Subway. A comparison with those of several state-of-the-art models illustrates its superiority and robustness. This study can provide critical experience in conducting short-term passenger flow predictions, especially from the perspective of real-world applications.

研究动机与目标

  • 解决在城市轨道交通客流预测中捕捉复杂时空依赖性的挑战。
  • 克服现有模型仅优化绝对误差、忽略空间与时间约束的局限性。
  • 减轻深度学习模型的计算负担与内存占用,提升实际部署可行性。
  • 设计一种轻量但强大的架构,在保持高预测精度的同时提升训练效率。

提出的方法

  • 提出一种结合门控时间卷积网络(TCN)与参数共享图卷积网络(GCN)的生成器网络,高效建模时间动态与空间拓扑结构。
  • 引入双判别器架构,包含空间判别器与时间判别器,以强化预测结果的结构一致性。
  • 通过对抗性方式联合训练生成器与判别器,提升预测结果的真实感与约束符合度。
  • 利用对抗损失引导生成器产出不仅准确,且在空间与时间上均合理可信的预测结果。
  • 利用基于图的轨道交通网络表示,编码车站连接关系与客流模式。
  • 采用混合损失函数,结合对抗损失、L1损失与时间一致性损失,以实现鲁棒的性能表现。

实验结果

研究问题

  • RQ1对抗性训练能否提升城市轨道交通系统中短时客流预测的现实感与约束符合度?
  • RQ2门控TCN与参数共享GCN的融合在不牺牲精度的前提下,如何提升建模效率?
  • RQ3相较于单判别器或无判别器基线模型,双判别器(空间与时间)在多大程度上提升了预测质量?
  • RQ4STG-GAN在真实世界数据上与最先进模型相比,在精度、推理速度与内存消耗方面表现如何?
  • RQ5所提模型在不同时间尺度与网络拓扑结构的城市轨道交通系统中是否具备良好的泛化能力?

主要发现

  • STG-GAN在两个大规模北京地铁数据集上,相比多种最先进模型,实现了更优的预测精度。
  • 由于GCN中的参数共享机制与轻量级TCN组件,模型展现出显著更低的内存占用与更高的训练效率。
  • 采用双判别器的对抗性训练有效提升了预测结果的空间与时间一致性,减少了不合理的客流波动。
  • 定量结果表明,STG-GAN在多种预测时长下,均优于基线模型的MAE、RMSE与MAPE指标。
  • 消融实验确认,空间与时间判别器均对性能提升有显著贡献。
  • 模型保持了较高的推理速度,适用于实际运营中城市轨道交通系统的实时部署。

更好的研究,从现在开始

从阅读论文到最终审阅,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。