HAGCN : Network Decentralization Attention Based Heterogeneity-Aware Spatiotemporal Graph Convolution Network for Traffic Signal Forecasting
This work improves traffic prediction accuracy for urban planning and management, though it is incremental as it builds on existing graph convolution network methods.
The paper tackled the problem of traffic signal forecasting by addressing the heterogeneous spatial relationships between sensors, which are typically modeled as homogeneous graphs, and achieved a 6.35% improvement over existing models with state-of-the-art performance.
The construction of spatiotemporal networks using graph convolution networks (GCNs) has become one of the most popular methods for predicting traffic signals. However, when using a GCN for traffic speed prediction, the conventional approach generally assumes the relationship between the sensors as a homogeneous graph and learns an adjacency matrix using the data accumulated by the sensors. However, the spatial correlation between sensors is not specified as one but defined differently from various viewpoints. To this end, we aim to study the heterogeneous characteristics inherent in traffic signal data to learn the hidden relationships between sensors in various ways. Specifically, we designed a method to construct a heterogeneous graph for each module by dividing the spatial relationship between sensors into static and dynamic modules. We propose a network decentralization attention based heterogeneity-aware graph convolution network (HAGCN) method that aggregates the hidden states of adjacent nodes by considering the importance of each channel in a heterogeneous graph. Experimental results on real traffic datasets verified the effectiveness of the proposed method, achieving a 6.35% improvement over the existing model and realizing state-of-the-art prediction performance.