Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neural Graph Navigation for Intelligent Subgraph Matching

Yuchen Ying, Yiyang Dai, Wenda Li, Wenjie Huang, Rui Wang, Tongya Zheng, Yu Wang, Hanyang Yuan, Mingli Song

TL;DR

NeuGN addresses the computational bottleneck of exact subgraph matching by injecting neural navigation into the enumeration phase while preserving completeness. It combines a Query Structure Extractor that produces a structural navigation signal with a Generative Graph Navigator that uses an Euler-guided Masked Nodes Sequence and a Transformer decoder to guide the search without pruning. The approach is plug-and-play with existing matchers and yields substantial reductions in First Match Steps and faster early convergence across six real-world datasets. This work demonstrates the practical impact of structure-aware neural guidance for large-scale graph pattern detection.

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.

Neural Graph Navigation for Intelligent Subgraph Matching

TL;DR

NeuGN addresses the computational bottleneck of exact subgraph matching by injecting neural navigation into the enumeration phase while preserving completeness. It combines a Query Structure Extractor that produces a structural navigation signal with a Generative Graph Navigator that uses an Euler-guided Masked Nodes Sequence and a Transformer decoder to guide the search without pruning. The approach is plug-and-play with existing matchers and yields substantial reductions in First Match Steps and faster early convergence across six real-world datasets. This work demonstrates the practical impact of structure-aware neural guidance for large-scale graph pattern detection.

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.

Paper Structure

This paper contains 41 sections, 9 equations, 8 figures, 8 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminaries
  4. Method
  5. Query Structure Extractor
  6. Generative Graph Navigator
  7. Training Strategy
  8. Plug-and-play Deployment of NeuGN
  9. Experiments
  10. Experimental setup
  11. Performance Comparison
  12. RQ1: FMS Comparison Across Algorithms and Datasets.
  13. RQ2: Ablation Study.
  14. RQ3: Impact of Navigation Depth.
  15. RQ4: Generalization to Different Query Sizes.
  16. ...and 26 more sections

Figures (8)

  • Figure 1: The illustrative diagram of NeuGN Framework.
  • Figure 2: The illustrative diagram of Generative Graph Navigator.
  • Figure 3: Local Candidate Nodes Batching Strategy.
  • Figure 4: Distribution of FMS Across All Queries.
  • Figure 5: Impact of Navigation Depth on FMS.
  • ...and 3 more figures

Theorems & Definitions (2)

  • proof
  • proof