HAGCN : Network Decentralization Attention Based Heterogeneity-Aware Spatiotemporal Graph Convolution Network for Traffic Signal Forecasting

TL;DR

This paper introduces HAGCN, a novel heterogeneity-aware spatiotemporal graph convolution network that models diverse sensor relationships for improved traffic signal forecasting, achieving state-of-the-art accuracy.

Contribution

The paper presents a new method to construct heterogeneous graphs and a decentralization attention mechanism for better traffic prediction.

Findings

Achieved 6.35% improvement over existing models.

Effectively models static and dynamic sensor relationships.

Realizes state-of-the-art traffic forecasting performance.

Abstract

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.