Neural Graph Navigation for Intelligent Subgraph Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ying, Yuchen, Dai, Yiyang, Li, Wenda, Huang, Wenjie, Wang, Rui, Zheng, Tongya, Wang, Yu, Yuan, Hanyang, Song, Mingli
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914167337779200
author Ying, Yuchen
Dai, Yiyang
Li, Wenda
Huang, Wenjie
Wang, Rui
Zheng, Tongya
Wang, Yu
Yuan, Hanyang
Song, Mingli
author_facet Ying, Yuchen
Dai, Yiyang
Li, Wenda
Huang, Wenjie
Wang, Rui
Zheng, Tongya
Wang, Yu
Yuan, Hanyang
Song, Mingli
contents Subgraph matching, a cornerstone of relational pattern detection in domains ranging from biochemical systems to social network analysis, faces significant computational challenges due to the dramatically growing search space. Existing methods address this problem within a filtering-ordering-enumeration framework, in which the enumeration stage recursively matches the query graph against the candidate subgraphs of the data graph. However, the lack of awareness of subgraph structural patterns leads to a costly brute-force enumeration, thereby critically motivating the need for intelligent navigation in subgraph matching. To address this challenge, we propose Neural Graph Navigation (NeuGN), a neuro-heuristic framework that transforms brute-force enumeration into neural-guided search by integrating neural navigation mechanisms into the core enumeration process. By preserving heuristic-based completeness guarantees while incorporating neural intelligence, NeuGN significantly reduces the \textit{First Match Steps} by up to 98.2\% compared to state-of-the-art methods across six real-world datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Graph Navigation for Intelligent Subgraph Matching
Ying, Yuchen
Dai, Yiyang
Li, Wenda
Huang, Wenjie
Wang, Rui
Zheng, Tongya
Wang, Yu
Yuan, Hanyang
Song, Mingli
Artificial Intelligence
Machine Learning
Subgraph matching, a cornerstone of relational pattern detection in domains ranging from biochemical systems to social network analysis, faces significant computational challenges due to the dramatically growing search space. Existing methods address this problem within a filtering-ordering-enumeration framework, in which the enumeration stage recursively matches the query graph against the candidate subgraphs of the data graph. However, the lack of awareness of subgraph structural patterns leads to a costly brute-force enumeration, thereby critically motivating the need for intelligent navigation in subgraph matching. To address this challenge, we propose Neural Graph Navigation (NeuGN), a neuro-heuristic framework that transforms brute-force enumeration into neural-guided search by integrating neural navigation mechanisms into the core enumeration process. By preserving heuristic-based completeness guarantees while incorporating neural intelligence, NeuGN significantly reduces the \textit{First Match Steps} by up to 98.2\% compared to state-of-the-art methods across six real-world datasets.
title Neural Graph Navigation for Intelligent Subgraph Matching
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.17939