Saved in:
Bibliographic Details
Main Authors: Xu, Ming, Xiang, Jinrong, Xie, Zilong, Meng, Xiangfu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.19199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915840566231040
author Xu, Ming
Xiang, Jinrong
Xie, Zilong
Meng, Xiangfu
author_facet Xu, Ming
Xiang, Jinrong
Xie, Zilong
Meng, Xiangfu
contents Existing learning-to-rank methods for road networks often fail to incorporate origin-destination (OD) flows and route information, limiting their ability to model long-range spatial dependencies. To address this gap, we propose HetGL2R, a heterogeneous graph learning framework for ranking road-segment importance. HetGL2R builds a tripartite graph that unifies OD flows, routes, and network topology, and further introduces attribute-guided graphs that elevate node attributes into explicit nodes to model functional similarity. A heterogeneous joint random walk algorithm (HetGWalk) jointly samples both graph types to generate context-rich node sequences. These sequences are encoded using a Transformer to learn embeddings that capture long-range structural dependencies induced by OD flows and route configurations, as well as functional associations derived from attribute similarity. Finally, a listwise ranking strategy with a KL-divergence loss evaluates and ranks segment importance. Experiments on three SUMO-generated simulated networks of different scales show that, against state-of-the-art methods, HetGL2R achieves average improvements of approximately 7.52%, 4.40% and 3.57% in ranking performance.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19199
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Rank Critical Road Segments via Heterogeneous Graphs with Origin-Destination Flow Integration
Xu, Ming
Xiang, Jinrong
Xie, Zilong
Meng, Xiangfu
Machine Learning
Existing learning-to-rank methods for road networks often fail to incorporate origin-destination (OD) flows and route information, limiting their ability to model long-range spatial dependencies. To address this gap, we propose HetGL2R, a heterogeneous graph learning framework for ranking road-segment importance. HetGL2R builds a tripartite graph that unifies OD flows, routes, and network topology, and further introduces attribute-guided graphs that elevate node attributes into explicit nodes to model functional similarity. A heterogeneous joint random walk algorithm (HetGWalk) jointly samples both graph types to generate context-rich node sequences. These sequences are encoded using a Transformer to learn embeddings that capture long-range structural dependencies induced by OD flows and route configurations, as well as functional associations derived from attribute similarity. Finally, a listwise ranking strategy with a KL-divergence loss evaluates and ranks segment importance. Experiments on three SUMO-generated simulated networks of different scales show that, against state-of-the-art methods, HetGL2R achieves average improvements of approximately 7.52%, 4.40% and 3.57% in ranking performance.
title Learning to Rank Critical Road Segments via Heterogeneous Graphs with Origin-Destination Flow Integration
topic Machine Learning
url https://arxiv.org/abs/2504.19199