MA2GCN: Multi Adjacency relationship Attention Graph Convolutional Networks for Traffic Prediction using Trajectory data
Zhengke Sun, Yuliang Ma
TL;DR
MA2GCN tackles traffic prediction by leveraging vehicle trajectory data to form graph-structured representations. It builds a mobility adjacency from grid-to-grid movements, introduces an adaptive graph generator, and applies a multi-adjacency attention mechanism to fuse $A$, $A^2$, $A_{dy}$, and $A_{mo}$ within a spatio-temporal framework that combines graph convolution and gated temporal convolution. The approach yields superior accuracy on the Shanghai taxi GPS dataset, outperforming strong baselines, and demonstrates the value of trajectory-driven, dynamic graph modeling for urban traffic. The work provides open-source code and highlights potential for adaptive grid partitioning and deeper trajectory connectivity analysis to further enhance predictive performance.
Abstract
The problem of traffic congestion not only causes a large amount of economic losses, but also seriously endangers the urban environment. Predicting traffic congestion has important practical significance. So far, most studies have been based on historical data from sensors placed on different roads to predict future traffic flow and speed, to analyze the traffic congestion conditions of a certain road segment. However, due to the fixed position of sensors, it is difficult to mine new information. On the other hand, vehicle trajectory data is more flexible and can extract traffic information as needed. Therefore, we proposed a new traffic congestion prediction model - Multi Adjacency relationship Attention Graph Convolutional Networks(MA2GCN). This model transformed vehicle trajectory data into graph structured data in grid form, and proposed a vehicle entry and exit matrix based on the mobility between different grids. At the same time, in order to improve the performance of the model, this paper also built a new adaptive adjacency matrix generation method and adjacency matrix attention module. This model mainly used gated temporal convolution and graph convolution to extract temporal and spatial information, respectively. Compared with multiple baselines, our model achieved the best performance on Shanghai taxi GPS trajectory dataset. The code is available at https://github.com/zachysun/Taxi_Traffic_Benchmark.