Neural Graph Navigation for Intelligent Subgraph Matching

TL;DR

This paper introduces Neural Graph Navigation (NeuGN), a neuro-heuristic framework that significantly improves subgraph matching efficiency by guiding the enumeration process with neural mechanisms, reducing search steps drastically.

Contribution

NeuGN is the first framework to integrate neural-guided search into subgraph matching, maintaining completeness guarantees while greatly enhancing efficiency.

Findings

NeuGN reduces First Match Steps by up to 98.2%

Achieves significant efficiency improvements across six datasets

Maintains heuristic-based completeness guarantees

Abstract

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.