Coupled Layer-wise Graph Convolution for Transportation Demand Prediction

TL;DR

This paper introduces a novel graph convolutional network with self-learned adjacency matrices and a layer-wise coupling mechanism, improving transportation demand prediction by capturing multi-level spatial and temporal dependencies.

Contribution

It proposes a new GCN architecture with adaptive, self-learned adjacency matrices and a layer-wise coupling mechanism, enhancing demand prediction accuracy.

Findings

Outperforms state-of-the-art models on NYC Citi Bike data.

Effectively captures multi-level spatial dependencies.

Demonstrates robustness across different datasets.

Abstract

Graph Convolutional Network (GCN) has been widely applied in transportation demand prediction due to its excellent ability to capture non-Euclidean spatial dependence among station-level or regional transportation demands. However, in most of the existing research, the graph convolution was implemented on a heuristically generated adjacency matrix, which could neither reflect the real spatial relationships of stations accurately, nor capture the multi-level spatial dependence of demands adaptively. To cope with the above problems, this paper provides a novel graph convolutional network for transportation demand prediction. Firstly, a novel graph convolution architecture is proposed, which has different adjacency matrices in different layers and all the adjacency matrices are self-learned during the training process. Secondly, a layer-wise coupling mechanism is provided, which associates the upper-level adjacency matrix with the lower-level one. It also reduces the scale of parameters in our model. Lastly, a unitary network is constructed to give the final prediction result by integrating the hidden spatial states with gated recurrent unit, which could capture the multi-level spatial dependence and temporal dynamics simultaneously. Experiments have been conducted on two real-world datasets, NYC Citi Bike and NYC Taxi, and the results demonstrate the superiority of our model over the state-of-the-art ones.