Hyper-GST: Predict Metro Passenger Flow Incorporating GraphSAGE, Hypergraph, Social-meaningful Edge Weights and Temporal Exploitation

TL;DR

This paper introduces Hyper-GST, a graph neural network model that predicts metro passenger flow by incorporating social-meaningful edge weights, hypergraph structures, and temporal data to address limitations of traditional deep learning methods.

Contribution

The study presents a novel GraphSAGE-based model with an edge weights learner, hypergraph, and temporal modules, enhancing metro passenger flow prediction accuracy.

Findings

Outperforms existing graph neural networks in passenger flow prediction

Effectively incorporates social-meaningful features for edge weighting

Improves prediction accuracy through hypergraph and temporal modules

Abstract

Predicting metro passenger flow precisely is of great importance for dynamic traffic planning. Deep learning algorithms have been widely applied due to their robust performance in modelling non-linear systems. However, traditional deep learning algorithms completely discard the inherent graph structure within the metro system. Graph-based deep learning algorithms could utilise the graph structure but raise a few challenges, such as how to determine the weights of the edges and the shallow receptive field caused by the over-smoothing issue. To further improve these challenges, this study proposes a model based on GraphSAGE with an edge weights learner applied. The edge weights learner utilises socially meaningful features to generate edge weights. Hypergraph and temporal exploitation modules are also constructed as add-ons for better performance. A comparison study is conducted on the proposed algorithm and other state-of-art graph neural networks, where the proposed algorithm could improve the performance.