Ling Huang
Abstract
As a critical task in intelligent traffic systems, traffic prediction has received a large amount of attention in the past few decades. The early efforts mainly model traffic prediction as the time-series mining problem, in which the spatial dependence has been largely ignored. As the rapid development of deep learning, some attempts have been made in modeling traffic prediction as the spatio-temporal data mining problem in a road network, in which deep learning techniques can be adopted for modeling the spatial and temporal dependencies simultaneously. Despite the success, the spatial and temporal dependencies are only modeled in a regionless network without considering the underlying hierarchical regional structure of the spatial nodes, which is an important structure naturally existing in the real-world road network. Apart from the challenge of modeling the spatial and temporal dependencies like the existing studies, the extra challenge caused by considering the hierarchical regional structure of the road network lies in simultaneously modeling the spatial and temporal dependencies between nodes and regions and the spatial and temporal dependencies between regions. To this end, this article proposes a new Temporal Hierarchical Graph Attention Network (TH-GAT). The main idea lies in augmenting the original road network into a region-augmented network, in which the hierarchical regional structure can be modeled. Based on the region-augmented network, the region-aware spatial dependence model and the region-aware temporal dependence model can be constructed, which are two main components of the proposed TH-GAT model. In addition, in the region-aware spatial dependence model, the graph attention network is adopted, in which the importance of a node to another node, of a node to a region, of a region to a node, and of a region to another region, can be captured automatically by means of the attention coefficients. Extensive experiments are conducted on two real-world traffic datasets, and the results have confirmed the superiority of the proposed TH-GAT model.
- [1] . 1998. DynaMIT: A simulation-based system for traffic prediction. In DACCORD Short Term Forecasting Workshop. 1–12.Google Scholar
- [2] . 1995. Neural Networks for Pattern Recognition. Oxford University Press. Google ScholarCross Ref
- [3] . 2012. The retrieval of intra-day trend and its influence on traffic prediction. Transport. Res. C: Emerg. Technol. 22 (2012), 103–118.Google ScholarCross Ref
- [4] . 2019. FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction. In Proceedings of the 23rd Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining (PAKDD’19), Vol. 11439. 265–279.Google ScholarDigital Library
- [5] . 2018. A neural attention model for urban air quality inference: Learning the weights of monitoring stations. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18). 2151–2158. Google ScholarDigital Library
- [6] . 2014. On the properties of neural machine translation: Encoder-decoder approaches. In Proceedings of the 8th Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST@EMNLP’14), , , , and (Eds.). 103–111.Google ScholarCross Ref
- [7] . 2003. Traffic prediction using multivariate nonparametric regression. J. Transport. Eng. 129, 2 (2003), 161–168.Google ScholarCross Ref
- [8] . 1996. Support vector regression machines. In Proceedings of the Advances in Neural Information Processing Systems (NIPS’96). 155–161. Google ScholarDigital Library
- [9] . 2020. Deep irregular convolutional residual LSTM for urban traffic passenger flows prediction. IEEE Trans. Intell. Transport. Syst. 21, 3 (2020), 972–985.Google ScholarCross Ref
- [10] . 2017. Deep convolutional neural networks for spatiotemporal crime prediction. In Proceedings of the International Conference on Information and Knowledge Engineering (IKE’17). 61–67.Google Scholar
- [11] . 2016. Classifying spatial trajectories using representation learning. Int. J. Data Sci. Anal. 2, 3–4 (2016), 107–117.Google ScholarCross Ref
- [12] . 2019. EEG-based spatio-temporal convolutional neural network for driver fatigue evaluation. IEEE Trans. Neural Netw. Learn. Syst. 30, 9 (2019), 2755–2763.Google ScholarCross Ref
- [13] . 2019. Short-term prediction of lane-level traffic speeds: A fusion deep learning model. Transport. Res. C: Emerg. Technol. 106 (2019), 1–16.Google ScholarCross Ref
- [14] . 2020. An improved Bayesian combination model for short-term traffic prediction with deep learning. IEEE Trans. Intell. Transport. Syst. 21, 3 (2020), 1332–1342.Google ScholarCross Ref
- [15] . 2006. Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504–507.Google ScholarCross Ref
- [16] . 1997. Long short-term memory. Neural Comput. 9, 8 (1997), 1735–1780. Google ScholarDigital Library
- [17] . 2020. MuMod: A micro-unit connection approach for hybrid-order community detection. In Proceedings of the AAAI International Conference on Artificial Intelligence (AAAI’20). 107–114.Google ScholarCross Ref
- [18] . 2014. Deep architecture for traffic flow prediction: Deep belief networks with multitask learning. IEEE Trans. Intell. Transport. Syst. 15, 5 (2014), 2191–2201.Google ScholarCross Ref
- [19] . 2002. Performance evaluation of short-term time-series traffic prediction model. J. Transport. Eng. 128, 6 (2002), 490–498.Google ScholarCross Ref
- [20] . 2019. PH-GCN: Person re-identification with part-based hierarchical graph convolutional network. CoRR abs/1907.08822.Google Scholar
- [21] . 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR’17).Google Scholar
- [22] . 2016. Improving traffic flow prediction with weather information in connected cars: A deep learning approach. IEEE Trans. Vehic. Technol. 65, 12 (2016), 9508–9517.Google ScholarCross Ref
- [23] . 2018. Exascale deep learning for climate analytics. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC’18). 649–660. Google ScholarDigital Library
- [24] . 2018. Deep representation learning for trajectory similarity computation. In Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE’18). 617–628.Google ScholarCross Ref
- [25] . 2019. From regional to global brain: A novel hierarchical spatial-temporal neural network model for EEG emotion recognition. IEEE Trans. Affect. Comput. (2019).Google ScholarCross Ref
- [26] . 2015. Traffic prediction in a bike-sharing system. In Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. 1–10. Google ScholarDigital Library
- [27] . 2018. Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach. Transport. Res. C: Emerg. Technol. 97 (2018), 258–276.Google ScholarCross Ref
- [28] . 2015. Traffic flow prediction with big data: A deep learning approach. IEEE Trans. Intell. Transport. Syst. 16, 2 (2015), 865–873.Google Scholar
- [29] . 2015. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transport. Res. C: Emerg. Technol. 54 (2015), 187–197.Google ScholarCross Ref
- [30] . 2011. Real-time road traffic prediction with spatio-temporal correlations. Transport. Res. C: Emerg. Technol. 19, 4 (2011), 606–616.Google ScholarCross Ref
- [31] . 2020. Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting. Inf. Sci. 521 (2020), 277–290.Google ScholarDigital Library
- [32] . 2017. Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies 79 (2017), 1–17.Google ScholarCross Ref
- [33] . 2014. A hidden markov model for short term prediction of traffic conditions on freeways. Transport. Res. C: Emerg. Technol. 43 (2014), 95–111.Google ScholarCross Ref
- [34] . 2011. Mining of Massive Datasets. Cambridge University Press. Google ScholarDigital Library
- [35] . 1999. Traffic prediction using FARIMA models. In Proceedings of the IEEE International Conference on Communications, Vol. 2. 891–895.Google Scholar
- [36] . 2014. Sequence to sequence learning with neural networks. In Proceedings of the Annual Conference on Neural Information Processing Systems. 3104–3112. Google ScholarDigital Library
- [37] . 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations (ICLR’18). OpenReview.net.Google Scholar
- [38] . 2019. Traffic speed prediction for urban transportation network: A path based deep learning approach. Transport. Res. C: Emerg. Technol. 100 (2019), 372–385.Google ScholarCross Ref
- [39] . 2020. SeqST-GAN: Seq2Seq generative adversarial nets for multi-step urban crowd flow prediction. ACM Trans. Spatial Algor. Syst. 6, 4 (2020), 22:1–22:24. Google ScholarDigital Library
- [40] . 2020. Deep learning for spatio-temporal data mining: A survey. IEEE Trans. Knowl. Data Eng. (2020).Google ScholarCross Ref
- [41] . 2020. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. (2020).Google Scholar
- [42] . 2017. An improved seasonal rolling grey forecasting model using a cycle truncation accumulated generating operation for traffic flow. Appl. Math. Model. 51 (2017), 386–404.Google ScholarCross Ref
- [43] . 2017. A neural network approach to jointly modeling social networks and mobile trajectories. ACM Trans. Inf. Syst. 35, 4 (2017), 36:1–36:28. Google ScholarDigital Library
- [44] . 2019. Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 5668–5675. Google ScholarDigital Library
- [45] . 2020. A comprehensive survey on traffic prediction. arXiv:2004.08555. Retrieved from https://arxiv.org/abs/2004.08555.Google Scholar
- [46] . 2017. Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks. Sensors 17, 7 (2017), 1501.Google ScholarCross Ref
- [47] . 2019. A hybrid traffic speed forecasting approach integrating wavelet transform and motif-based graph convolutional recurrent neural network. CoRR abs/1904.06656 (2019).Google Scholar
- [48] . 2019. Spatial-temporal recurrent neural network for emotion recognition. IEEE Trans. Cybern. 49, 3 (2019), 839–847.Google ScholarCross Ref
- [49] . 2019. GCGAN: Generative adversarial nets with graph CNN for network-scale traffic prediction. In Proceedings of the International Joint Conference on Neural Networks (IJCNN’19). 1–8.Google ScholarCross Ref
- [50] . 2019. TrafficGAN: Network-scale deep traffic prediction with generative adversarial nets. IEEE Trans. Intell. Transport. Syst. (2019).Google Scholar
- [51] . 2020. T-GCN: A temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transport. Syst. 21, 9 (2020), 3848–3858.Google ScholarCross Ref
Index Terms
- Temporal Hierarchical Graph Attention Network for Traffic Prediction
Recommendations
Traffic Flow Prediction via Spatial Temporal Graph Neural Network
WWW '20: Proceedings of The Web Conference 2020Traffic flow analysis, prediction and management are keystones for building smart cities in the new era. With the help of deep neural networks and big traffic data, we can better understand the latent patterns hidden in the complex transportation ...
A trend graph attention network for traffic prediction
Highlights- Fine-grained modeling of temporal heterogeneity and spatial heterogeneity.
- ...
AbstractTraffic prediction is an important part of urban computing. Accurate traffic prediction assists the public in planning travel routes and relevant departments in traffic management, thus improving the efficiency of people’s travel. ...
Multi-graph fusion based graph convolutional networks for traffic prediction
AbstractTraffic prediction is significant for transportation management and travel route planning, and it is challenging as the spatial dependencies are complex and temporal patterns are dynamic. Local spatial dependencies exist between nodes nearby, and ...
Comments