MetroGNN: Metro Network Expansion with Reinforcement Learning

TL;DR

MetroGNN addresses the NP-hard metro network expansion problem by modeling it as a Markov decision process on a heterogeneous multi-graph. It integrates a graph neural network encoder to capture spatial contiguity and OD-flow signals and employs a masked attentive policy to navigate the combinatorial action space under budget constraints. Empirical results on real data from Beijing and Changsha show MetroGNN substantially improves satisfied OD flow by over 30% compared with state-of-the-art baselines, with robust performance in complex scenarios. This work advances graph-based reinforcement learning for urban planning, offering a scalable approach with potential applications beyond transit planning.

Abstract

Selecting urban regions for metro network expansion to meet maximal transportation demands is crucial for urban development, while computationally challenging to solve. The expansion process relies not only on complicated features like urban demographics and origin-destination (OD) flow but is also constrained by the existing metro network and urban geography. In this paper, we introduce a reinforcement learning framework to address a Markov decision process within an urban heterogeneous multi-graph. Our approach employs an attentive policy network that intelligently selects nodes based on information captured by a graph neural network. Experiments on real-world urban data demonstrate that our proposed methodology substantially improve the satisfied transportation demands by over 30\% when compared with state-of-the-art methods. Codes are published at https://github.com/tsinghua-fib-lab/MetroGNN.

Figures (4)

• Figure 1: (a) Regions determined by road network. (b) Heterogeneous multi-graph, where nodes represents regions. The black solid line and the orange dashed line correspond to spatial contiguity and OD associations between regions. (c) Schematic of our approach.
• Figure 2: (a) The schematic of metro network expansion process. At each step, the agent selects a node that either extends existing lines ($a_0$) or constructs new lines ($a_1$). We use distinct colors for different lines, and purple for interchange. (b) The proposed GNN model, where a spatial-aware and OD-aware message passing mechanism is developed. (c) The proposed masked attentive policy network for node selection.
• Figure 3: Visualization of metro network expansion for Beijing. We use colors to distinguish between different metro lines, and use boldface nodes to indicate expansion solution. Black nodes indicate stations on the initial lines and their extensions, and red nodes represent stations on new lines. Regions colored with red and green indicate areas where population and POIs are clustered, respectively. The darker the color, the higher the density.
• Figure 4: Performance of MetroGNN and its variants that remove different elements, including whole graph model (G), spatial edges (Et), transportation flow edges (Eo), OD direct (FD) and auxiliary (FA) features. Best viewed in color.