【论文阅读】Spatio-Temporal Graph Convolutional Networks:...Traffic Forecasting[时空图卷积网络:用于交通预测的深度学习框架]（1）

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
时空图卷积网络:用于交通预测的深度学习框架

原文地址：https://transport.ckcest.cn/Search/get/298151?db=cats_huiyi_jtxs

0. Abstract

Abstract: Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, tradi- tional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN) , to tackle the time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem on graphs and build the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Experiments show that our model STGCN effec- tively captures comprehensive spatio-temporal correlations through modeling multi-scale traffic net- works and consistently outperforms state-of-the-art baselines on various real-world traffic datasets.
摘要：及时准确的交通预测对城市交通控制和引导至关重要。由于交通流的高度非线性和复杂性，传统的交通流预测方法不能满足中长期交通流预测的要求，往往忽略了交通流的时空相关性。本文提出了一种新的深度学习框架—— 时空图卷积网络(spatial - temporal Graph Convolutional Networks, STGCN) 来解决交通领域的时间序列预测问题。我们不使用正则卷积和递归单元，而是将问题表达在图上，并建立具有完整卷积结构的模型，这样可以用较少的参数获得更快的训练速度。实验表明，我们的模型STGCN通过建模多尺度交通网络有效地捕获全面的时空相互关系，并始终优于各种现实世界交通数据集的最先进的基线。

1. Introduction（介绍）

 Transportation plays a vital role in everybody’s daily life. According to a survey in 2015, U.S. drivers spend about 48 minutes on average behind the wheel daily.1 Under this circumstance, accurate real-time forecast of traffic conditions is of paramount importance for road users, private sectors and governments. Widely used transportation services, such as flow control, route planning, and navigation, also rely heavily on a high-quality traffic condition evaluation. In general, multi- scale traffic forecast is the premise and foundation of urban traffic control and guidance, which is also one of main functions of the Intelligent Transportation System (ITS).
 交通在每个人的日常生活中起着至关重要的作用。根据2015年的一项调查，美国司机平均每天花48分钟在方向盘上在这种情况下，准确实时的交通状况预测，对道路使用者、私营部门和政府来说，是至关重要的。广泛使用的交通服务，如流量控制、路线规划和导航，也在很大程度上依赖于高质量的交通状况评估。总体而言，多尺度交通预测是城市交通控制与引导的前提和基础，也是智能交通系统(ITS)的主要功能之一。

 In the traffic study, fundamental variables of traffic flow, namely speed, volume, and density are typically chosen as indicators to monitor the current status of traffic conditions and to predict the future. Based on the length of prediction, traffic forecast is generally classified into two scales: short-term (5~30 min), medium and long term (over 30 min). Most prevalent statistical approaches (for example, linear regression) are able to perform well on short interval forecast. However, due to the uncertainty and complexity of traffic flow, those methods are less effective for relatively long-term predictions.
 在交通研究中，通常选择交通流的基本变量，即速度、流量和密度作为监测交通状况的当前状态和预测未来的指标。根据预测长度，交通预测一般分为短期(5~30 min)、中期和长期(30 min以上)两个尺度。大多数流行的统计方法(例如，线性回归)能够在短区间预测中表现良好。然而，由于交通流的不确定性和复杂性，这些方法对于相对长期的预测效果较差。

 Previous studies on mid-and-long term traffic prediction can be roughly divided into two categories: dynamical modeling and data-driven methods. Dynamical modeling uses mathematical tools (e.g. differential equations) and physi- cal knowledge to formulate traffic problems by computational simulation [Vlahogianni, 2015] . To achieve a steady state, the simulation process not only requires sophisticated systematic programming but also consumes massive computational power. Impractical assumptions and simplifications among the modeling also degrade the prediction accuracy. Therefore, with rapid development of traffic data collection and storage techniques, a large group of researchers are shifting their attention to data-driven approaches.
 以往关于中长期交通预测的研究大致可分为动态建模和数据驱动方法两大类。动力学建模使用数学工具(如微分方程)和物理知识，通过计算模拟来制定交通问题 [Vlahogianni, 2015] 。为了达到稳态，仿真过程不仅需要复杂的系统编程，而且需要消耗大量的计算能力。模型中不切实际的假设和简化也会降低预测精度。因此，随着交通数据采集和存储技术的快速发展，一大批研究人员正将注意力转向数据驱动的方法。

 Classic statistical and machine learning models are two major representatives of data-driven methods. In time- series analysis, autoregressive integrated moving average (ARIMA) and its variants are one of the most consolidated approaches based on classical statistics [Ahmed and Cook, 1979; Williams and Hoel, 2003] . However, this type of model is limited by the stationary assumption of time sequences and fails to take the spatio-temporal correlation into account. Therefore, these approaches have constrained representability of highly nonlinear traffic flow. Recently, classic statistical models have been vigorously challenged by machine learning methods on traffic prediction tasks. Higher prediction accuracy and more complex data modeling can be achieved by these models, such as k-nearest neighbors algorithm (KNN), support vector machine (SVM), and neural networks (NN).
 经典的统计模型和机器学习模型是数据驱动方法的两个主要代表。在时间序列分析中，自回归综合移动平均(ARIMA)及其变体是基于经典统计的最统一的方法之一 [Ahmed and Cook, 1979; Williams and Hoel, 2003] 。然而，这类模型受时间序列平稳假设的限制，未能考虑到时空相关性。因此，这些方法限制了高度非线性交通流的可表征性。近年来，经典的统计模型受到了交通预测任务中的机器学习方法的挑战。这些模型可以实现更高的预测精度和更复杂的数据建模，如k近邻算法(KNN)、支持向量机(SVM)和神经网络(NN)。

 Deep learning approaches have been widely and successfully applied to various traffic tasks nowadays. Significant progress has been made in related work, for instance, deep belief network (DBN) [Jia et al., 2016; Huang et al., 2014] , stacked autoencoder (SAE) [Lv et al., 2015; Chen et al., 2016] . However, it is difficult for these dense networks to extract spatial and temporal features from the input jointly. Moreover, within narrow constraints or even com- plete absence of spatial attributes, the representative ability of these networks would be hindered seriously.
 深度学习方法 目前已经被广泛成功地应用于各种交通任务中。相关工作取得了显著进展，如深度信念网络(DBN) [Jia et al., 2016; Huang et al., 2014] ，stacked autoencoder (SAE) [Lv et al., 2015; Chen et al., 2016] 。然而，这些密集的网络很难从输入中联合提取时空特征。此外，在狭窄的约束条件下，甚至在完全缺乏空间属性的情况下，这些网络的代表能力将受到严重的阻碍。

 To take full advantage of spatial features, some researchers use convolutional neural network (CNN) to capture adjacent relations among the traffic network, along with employing recurrent neural network (RNN) on time axis. By combining long short-term memory (LSTM) network [Hochreiter and Schmidhuber, 1997] and 1-D CNN, Wu and Tan [2016] presented a feature-level fused architecture CLTFP for short-term traffic forecast. Although it adopted a straightforward strategy, CLTFP still made the first attempt to align spatial and temporal regularities. Afterwards, Shi et al. [2015] proposed the convolutional LSTM, which is an extended fully- connected LSTM (FC-LSTM) with embedded convolutional layers. However, the normal convolutional operation applied restricts the model to only process grid structures (e.g. images, videos) rather than general domains. Meanwhile, recurrent networks for sequence learning require iterative training, which introduces error accumulation by steps. Additionally, RNN-based networks (including LSTM) are widely known to be difficult to train and computationally heavy.
 为了充分利用空间特征，一些研究人员使用卷积神经网络(CNN)捕捉交通网络之间的相邻关系，并在时间轴上使用回归神经网络(RNN)。Wu and Tan [2016] 结合长短时记忆(LSTM)网络 [Hochreiter and Schmidhuber, 1997] 和一维CNN，提出了一种用于短期交通预测的特征级融合架构CLTFP。尽管它采用了一个直截了当的策略，CLTFP仍然第一次尝试对齐空间和时间的规律。随后，Shi et al. [2015] 提出了卷积LSTM，它是一种嵌入卷积层的扩展全连通LSTM (FC-LSTM)。然而，常规的卷积运算限制模型只能处理网格结构(如图像、视频)，而不能处理一般领域。同时，用于序列学习的递归网络需要迭代训练，引入了误差逐步积累。此外，众所周知，基于RNN的网络(包括LSTM)训练困难且计算量大。

 For overcoming these issues, we introduce several strategies to effectively model temporal dynamics and spatial dependencies of traffic flow. To fully utilize spatial information, we model the traffic network by a general graph instead of treating it separately (e.g. grids or segments). To handle the inherent deficiencies of recurrent networks, we employ a fully convolutional structure on time axis. Above all, we propose a novel deep learning architecture, the spatio-temporal graph convolutional networks, for traffic forecasting tasks. This architecture comprises several spatio-temporal convolutional blocks, which are a combination of graph convolutional layers [Defferrard et al., 2016] and convolutional sequence learning layers, to model spatial and temporal dependencies. To the best of our knowledge, it is the first time that to apply purely convolutional structures to extract spatio-temporal features simultaneously from graph-structured time series in a traffic study. We evaluate our proposed model on two real-world traffic datasets. Experiments show that our framework outperforms existing baselines in prediction tasks with multiple preset prediction lengths and network scales.
 为了克服这些问题，我们引入了几种策略来有效地建模交通流的时间动力学和空间依赖性。为了充分利用空间信息，我们用一般图形来建模交通网络，而不是单独对待它(如网格或分段)。为了解决递归网络的固有缺陷，我们采用了时间轴上的全卷积结构。首先，我们提出了一种新的深度学习架构——时空图卷积网络，用于交通预测任务。该架构包括几个时空卷积块，它们是图卷积层 [Defferrard et al., 2016] 和卷积序列学习层的组合，以建模空间和时间依赖性。据我们所知，在交通研究中应用纯卷积结构同时从图结构时间序列中提取时空特征尚属首次。我们在两个真实世界的交通数据集上评估我们提出的模型。实验表明，该框架在具有多个预估长度和网络规模的预测任务中性能优于现有的基线。

参考文献

[Vlahogianni, 2015] Eleni I Vlahogianni. Computational intelligence and optimization for transportation big data: challenges and opportunities. In Engineering and Applied Sciences Optimization, pages 107–128. Springer, 2015.

[Ahmed and Cook, 1979] Mohammed S Ahmed and Allen R Cook. Analysis of freeway traffic time-series data by using Box-Jenkins techniques. 1979.

[Williams and Hoel, 2003] Billy M Williams and Lester A Hoel. Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results. Journal of transportation engineering, 129(6):664–672, 2003.

[Jia et al., 2016] Yuhan Jia, Jianping Wu, and Yiman Du. Traffic speed prediction using deep learning method. In ITSC, pages 1217–1222. IEEE, 2016.

[Huang et al., 2014] Wenhao Huang, Guojie Song, Haikun Hong, and Kunqing Xie. Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Transactions on Intelligent Transportation Systems, 15(5):2191–2201, 2014.

[Lv et al., 2015] Yisheng Lv, Yanjie Duan, Wenwen Kang, Zhengxi Li, and FeiYue Wang. Traffic flow prediction with big data: a deep learning approach. IEEE Trans- actions on Intelligent Transportation Systems, 16(2):865–873, 2015.

[Chen et al., 2016] Quanjun Chen, Xuan Song, Harutoshi Yamada, and Ryosuke Shibasaki. Learning deep representation from big and heterogeneous data for traffic accident inference. In AAAI, pages 338–344, 2016.

[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Ju¨rgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997.

[Wu and Tan, 2016] Yuankai Wu and Huachun Tan. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework. arXiv preprint arXiv:1612.01022, 2016.

[Shi et al., 2015] Xingjian Shi, Zhourong Chen, Hao Wang, DitYan Yeung, WaiKin Wong, and Wangchun Woo. Convolutional lstm network: A machine learning approach for precipitation nowcasting. In NIPS, pages 802–810, 2015.

[Defferrard et al., 2016] Michae¨l Defferrard, Xavier Bresson, and Pierre Vandergheynst. Convolutional neural networks on graphs with fast localized spectral filtering. In NIPS, pages 3844–3852, 2016.