Interpretable Spatiotemporal Deep Learning Model for Traffic Flow Prediction Based on Potential Energy Fields

Ji, Jiahao; Wang, Jing‐Yuan; Jiang, Zhe; Ma, Jingtian; Zhang, Hu

doi:10.1109/icdm50108.2020.00128

Cited by 16 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there has been an increasing amount of literature on the interpretability of deep learning (Wang et al 2019a(Wang et al ,b, 2020b(Wang et al , 2022Wang, Feng, and Wu 2019;Cong et al 2021;Ji et al 2020Ji et al , 2022, one of which is feature importance analysis. The first group propagates an importance score from the output neuron backward to the input.…”

Section: Related Workmentioning

confidence: 99%

Full Bayesian Significance Testing for Neural Networks

Liu,

Li,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing often needs to derive the distribution of the testing statistic, failing to deal with complex nonlinear relationships. In this paper, we propose to conduct Full Bayesian Significance Testing for neural networks, called nFBST, to overcome the limitation in relationship characterization of traditional approaches. A Bayesian neural network is utilized to fit the nonlinear and multi-dimensional relationships with small errors and avoid hard theoretical derivation by computing the evidence value. Besides, nFBST can test not only global significance but also local and instance-wise significance, which previous testing methods don't focus on. Moreover, nFBST is a general framework that can be extended based on the measures selected, such as Grad-nFBST, LRP-nFBST, DeepLIFT-nFBST, LIME-nFBST. A range of experiments on both simulated and real data are conducted to show the advantages of our method.

show abstract

Section: Related Workmentioning

confidence: 99%

Full Bayesian Significance Testing for Neural Networks

Liu,

Li,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…In recent years, more and more researchers have employed deep learning models to solve traffic prediction problems. Early on, convolutional neural networks (CNNs) were applied to grid-based traffic data to capture spatial dependencies in the data (Wang et al 2016;Zhang, Zheng, and Qi 2017;Yao et al 2018;Lin et al 2020a the powerful ability to model graph data, graph neural networks (GNNs) were widely used for traffic prediction (Li et al 2018;Yu, Yin, and Zhu 2018;Wu et al 2019;Ji et al 2020;Chen et al 2020;Ye et al 2021;Wu et al 2020;Zhang et al 2021;Song et al 2020;Li and Zhu 2021;Oreshkin et al 2021;Han et al 2021;Ji et al 2022;Fang et al 2021;Choi et al 2022;Liu et al 2022). Recently, the attention mechanism has become increasingly popular due to its effectiveness in modeling the dynamic dependencies in traffic data (Guo et al 2019;Wang et al 2020;Lin et al 2020b;Yan and Ma 2021;Ye et al 2022).…”

Section: Related Work Deep Learning For Traffic Predictionmentioning

confidence: 99%

PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction

Jiang

Han

Zhao

et al. 2023

AAAI

View full text Add to dashboard Cite

As a core technology of Intelligent Transportation System, traffic flow prediction has a wide range of applications. The fundamental challenge in traffic flow prediction is to effectively model the complex spatial-temporal dependencies in traffic data. Spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising methods to solve this problem. However, GNN-based models have three major limitations for traffic prediction: i) Most methods model spatial dependencies in a static manner, which limits the ability to learn dynamic urban traffic patterns; ii) Most methods only consider short-range spatial information and are unable to capture long-range spatial dependencies; iii) These methods ignore the fact that the propagation of traffic conditions between locations has a time delay in traffic systems. To this end, we propose a novel Propagation Delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. Specifically, we design a spatial self-attention module to capture the dynamic spatial dependencies. Then, two graph masking matrices are introduced to highlight spatial dependencies from short- and long-range views. Moreover, a traffic delay-aware feature transformation module is proposed to empower PDFormer with the capability of explicitly modeling the time delay of spatial information propagation. Extensive experimental results on six real-world public traffic datasets show that our method can not only achieve state-of-the-art performance but also exhibit competitive computational efficiency. Moreover, we visualize the learned spatial-temporal attention map to make our model highly interpretable.

show abstract

“…According to the scope, the traffic prediction can be aimed at individuals, roads, and the whole urban areas. For example, [11,40] predicted an individual's trajectory based on their location history; [1,45] aimed to predict traffic speed and traffic volume on the road; [7,15,8] are methods for the city scale regional traffic prediction; In addition, there are some special traffic prediction tasks: [17] focused on interpretability, and proposed an interpretable deep learning model for traffic flow prediction. [52] aimed to estimate the traffic after new buildings were constructed.…”

Section: Related Workmentioning

confidence: 99%

Urban Regional Function Guided Traffic Flow Prediction

Kuo¹,

Liu²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest. In addition to spatial-temporal correlations, the functionality of urban areas also plays a crucial role in traffic flow prediction. However, the exploration of regional functional attributes mainly focuses on adding additional topological structures, ignoring the influence of functional attributes on regional traffic patterns. Different from the existing works, we propose a novel module named POI-MetaBlock, which utilizes the functionality of each region (represented by Point of Interest distribution) as metadata to further mine different traffic characteristics in areas with different functions. Specifically, the proposed POI-MetaBlock employs a self-attention architecture and incorporates POI and time information to generate dynamic attention parameters for each region, which enables the model to fit different traffic patterns of various areas at different times. Furthermore, our lightweight POI-MetaBlock can be easily integrated into conventional traffic flow prediction models. Extensive experiments demonstrate that our module significantly improves the performance of traffic flow prediction and outperforms state-of-the-art methods that use metadata.

show abstract

Interpretable Spatiotemporal Deep Learning Model for Traffic Flow Prediction Based on Potential Energy Fields

Cited by 16 publications

References 12 publications

Full Bayesian Significance Testing for Neural Networks

Full Bayesian Significance Testing for Neural Networks

PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction

Urban Regional Function Guided Traffic Flow Prediction

Contact Info

Product

Resources

About