Structural and topological guided GCN for link prediction in temporal networks

Sserwadda, Abubakhari; Özcan, Alper; Yaslan, Yusuf

doi:10.1007/s12652-023-04639-0

Cited by 2 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extraction of temporal dependencies. Traffic forecasting extensively employs recurrent neural networks (RNNs) because of their capacity to memorize and learn both short-and long-term temporal dependencies in sequences [5,7,22,[31][32][33]. However, if the dataset is large, the computational load of gating in the RNNs will be large.…”

Section: Related Workmentioning

confidence: 99%

ADSTGCN: A Dynamic Adaptive Deeper Spatio-Temporal Graph Convolutional Network for Multi-Step Traffic Forecasting

Cui

Noh

Park

2023

Sensors

View full text Add to dashboard Cite

Multi-step traffic forecasting has always been extremely challenging due to constantly changing traffic conditions. Advanced Graph Convolutional Networks (GCNs) are widely used to extract spatial information from traffic networks. Existing GCNs for traffic forecasting are usually shallow networks that only aggregate two- or three-order node neighbor information. Because of aggregating deeper neighborhood information, an over-smoothing phenomenon occurs, thus leading to the degradation of model forecast performance. In addition, most existing traffic forecasting graph networks are based on fixed nodes and therefore need more flexibility. Based on the current problem, we propose Dynamic Adaptive Deeper Spatio-Temporal Graph Convolutional Networks (ADSTGCN), a new traffic forecasting model. The model addresses over-smoothing due to network deepening by using dynamic hidden layer connections and adaptively adjusting the hidden layer weights to reduce model degradation. Furthermore, the model can adaptively learn the spatial dependencies in the traffic graph by building the parameter-sharing adaptive matrix, and it can also adaptively adjust the network structure to discover the unknown dynamic changes in the traffic network. We evaluated ADSTGCN using real-world traffic data from the highway and urban road networks, and it shows good performance.

show abstract