Skeleton-Guided Learning for Shortest Path Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Tiantian, Li, Xiao, Li, Huan, Lu, Hua, Jensen, Christian S., Xu, Jianliang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916879557197824
author Liu, Tiantian
Li, Xiao
Li, Huan
Lu, Hua
Jensen, Christian S.
Xu, Jianliang
author_facet Liu, Tiantian
Li, Xiao
Li, Huan
Lu, Hua
Jensen, Christian S.
Xu, Jianliang
contents Shortest path search is a core operation in graph-based applications, yet existing methods face important limitations. Classical algorithms such as Dijkstra's and A* become inefficient as graphs grow more complex, while index-based techniques often require substantial preprocessing and storage. Recent learning-based approaches typically focus on spatial graphs and rely on context-specific features like geographic coordinates, limiting their general applicability. We propose a versatile learning-based framework for shortest path search on generic graphs, without requiring domain-specific features. At the core of our approach is the construction of a skeleton graph that captures multi-level distance and hop information in a compact form. A Skeleton Graph Neural Network (SGNN) operates on this structure to learn node embeddings and predict distances and hop lengths between node pairs. These predictions support LSearch, a guided search algorithm that uses model-driven pruning to reduce the search space while preserving accuracy. To handle larger graphs, we introduce a hierarchical training strategy that partitions the graph into subgraphs with individually trained SGNNs. This structure enables HLSearch, an extension of our method for efficient path search across graph partitions. Experiments on five diverse real-world graphs demonstrate that our framework achieves strong performance across graph types, offering a flexible and effective solution for learning-based shortest path search.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skeleton-Guided Learning for Shortest Path Search
Liu, Tiantian
Li, Xiao
Li, Huan
Lu, Hua
Jensen, Christian S.
Xu, Jianliang
Machine Learning
Databases
Shortest path search is a core operation in graph-based applications, yet existing methods face important limitations. Classical algorithms such as Dijkstra's and A* become inefficient as graphs grow more complex, while index-based techniques often require substantial preprocessing and storage. Recent learning-based approaches typically focus on spatial graphs and rely on context-specific features like geographic coordinates, limiting their general applicability. We propose a versatile learning-based framework for shortest path search on generic graphs, without requiring domain-specific features. At the core of our approach is the construction of a skeleton graph that captures multi-level distance and hop information in a compact form. A Skeleton Graph Neural Network (SGNN) operates on this structure to learn node embeddings and predict distances and hop lengths between node pairs. These predictions support LSearch, a guided search algorithm that uses model-driven pruning to reduce the search space while preserving accuracy. To handle larger graphs, we introduce a hierarchical training strategy that partitions the graph into subgraphs with individually trained SGNNs. This structure enables HLSearch, an extension of our method for efficient path search across graph partitions. Experiments on five diverse real-world graphs demonstrate that our framework achieves strong performance across graph types, offering a flexible and effective solution for learning-based shortest path search.
title Skeleton-Guided Learning for Shortest Path Search
topic Machine Learning
Databases
url https://arxiv.org/abs/2508.02270