MGL2Rank: Learning to Rank the Importance of Nodes in Road Networks Based on Multi-Graph Fusion

20 May 2023  ·  Ming Xu, Jing Zhang ·

Identifying important nodes with strong propagation capabilities in road networks is a significant topic in the field of urban planning. However, existing methods for evaluating the importance of nodes in traffic network consider only topological information and traffic volumes, ignoring the diversity of characteristics in road networks, such as the number of lanes and average speed of road segments, limiting their performance. To solve this problem, we propose a graph learning-based framework (MGL2Rank) that integrates the rich characteristics of road network for ranking the importance of nodes. In this framework, we first develop an embedding module that contains a sampling algorithm (MGWalk) and an encoder network to learn latent representation for each road segment. MGWalk utilizes multi-graph fusion to capture the topology of the road network and establish associations among road segments based on their attributes. Then, we use the obtained node representation to learn the importance ranking of road segments. Finally, we construct a synthetic dataset for ranking tasks based on the regional road network of Shenyang city, and our ranking results on this dataset demonstrate the effectiveness of our proposed method. The data and source code of MGL2Rank are available at https://github.com/ZJ726.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods