Ollivier–Ricci Curvature Based Spatio-Temporal Graph Neural Networks for Traffic Flow Forecasting

Abstract

Traffic flow forecasting is a basic function of intelligent transportation systems, and the accuracy of prediction is of great significance for traffic management and urban planning. The main difficulty of traffic flow predictions is that there is complex underlying spatiotemporal dependence in traffic flow; thus, the existing spatiotemporal graph neural network (STGNN) models need to model both temporal dependence and spatial dependence. Graph neural networks (GNNs) are adopted to capture the spatial dependence in traffic flow, which can model the symmetric or asymmetric spatial relations between nodes in the traffic network. The transmission process of traffic features in GNNs is guided by the node-to-node relationship (e.g., adjacency or spatial distance) between nodes, ignoring the spatial dependence caused by local topological constraints in the road network. To further consider the influence of local topology on the spatial dependence of road networks, in this paper, we introduce Ollivier–Ricci curvature information between connected edges in the road network, which is based on optimal transport theory and makes comprehensive use of the neighborhood-to-neighborhood relationship to guide the transmission process of traffic features between nodes in STGNNs. Experiments on real-world traffic datasets show that the models with Ollivier–Ricci curvature information outperforms those based on only node-to-node relationships between nodes by ten percent on average in the RMSE metric. This study indicates that by utilizing complex topological features in road networks, spatial dependence can be captured more sufficiently, further improving the predictive ability of traffic forecasting models.

Dynamic Spatiotemporal Correlation Graph Convolutional Network for Traffic Speed Prediction

“…Although this method is more effective at capturing the dynamic spatiotemporal correlations of the road network compared to static adjacency matrices, when dealing with missing or sparse At present, there have been many studies on traffic prediction, but these methods still cannot account for the dynamic correlations between traffic nodes and complex spatiotemporal features. In these models, CNN [3] and GCN [4] are commonly used to extract spatial features from traffic data. However, the structure of traffic networks often exhibits asymmetric and irregular properties, and the CNN is limited by its inability to process non-Euclidean data.…”

Special Issue: Machine Learning and Data Analysis

“…Time series forecasting [1][2][3][4][5]; • Image analysis [6]; • Medical applications [7,8]; • Knowledge graph analysis [9,10]; • Cybersecurity [11][12][13]; • Traffic analysis [14,15]; • Agriculture [16]; • Environmental data analysis [17].…”

“…The authors of [15] focused more on the topological aspects of traffic analysis, proposing the Ollivier-Ricci curvature [23] to measure possible bottlenecks in the network.…”