Neural Graph Navigation for Intelligent Subgraph Matching

2025-11-22

AI Summary

Subgraph matching suffers from severe efficiency bottlenecks in domains such as biochemical systems and social networks due to exponential search-space explosion. Existing filter-sort-enumerate approaches rely on brute-force recursive enumeration and lack awareness of subgraph structural patterns, resulting in prohibitive computational overhead. This paper proposes the first neural graph navigation framework, reformulating traditional enumeration as neural-guided intelligent path search. By jointly encoding graph topology and learning dynamic navigation policies, our method integrates structural feature representation with matching heuristics while preserving completeness and enabling optimal path selection. Crucially, we embed the neural navigation mechanism directly into the core enumeration phase, synergistically combining interpretable domain rules with end-to-end learning. Evaluated on six real-world datasets, our approach reduces the number of matching steps by up to 98.2% over state-of-the-art methods, significantly improving both matching efficiency and scalability.

Technology Category

• Search and Optimization: Heuristic Search
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

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 extit{First Match Steps} by up to 98.2% compared to state-of-the-art methods across six real-world datasets.

Problem

• Subgraph matching faces computational challenges from growing search spaces
• Existing methods lack awareness of subgraph structural patterns
• Neural Graph Navigation transforms brute-force enumeration into neural-guided search

Innovation

• Transforms brute-force enumeration into neural-guided search
• Integrates neural navigation mechanisms into enumeration process
• Preserves heuristic-based completeness while incorporating neural intelligence