Difference between revisions of "Spatial-Temporal Dynamic Network (STDN)"
| Line 10: | Line 10: | ||
* [[Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning]] | * [[Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning]] | ||
* [[Memory Networks]] | * [[Memory Networks]] | ||
| − | + | * [[3D Model]] | |
| + | * [[Passenger Screening]] Challenge | ||
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. [http://arxiv.org/abs/1803.01254 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction | H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li] | 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. [http://arxiv.org/abs/1803.01254 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction | H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li] | ||
Revision as of 08:01, 27 July 2019
YouTube Search ...Google search
- Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning
- Memory Networks
- 3D Model
- Passenger Screening Challenge
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. Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction | H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li
