Hierarchy-Aware Neural Subgraph Matching With Enhanced Similarity Measure

Subgraph matching is challenging as it necessitates time-consuming combinatorial searches. Recent Graph Neural Network (GNN)-based approaches address this issue by employing GNN encoders to extract graph information and hinge distance measures to ensure containment constraints in the embedding space...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on knowledge and data engineering Jg. 37; H. 9; S. 5298 - 5310
Hauptverfasser: Liu, Zhouyang, Liu, Ning, Chen, Yixin, He, Jiezhong, Jia, Menghan, Li, Dongsheng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.09.2025
Schlagworte:
Approximation algorithms
Data mining
Distortion measurement
Encoding
Fasteners
graph neural network
Graph neural networks
Graph representation learning
Loss measurement
Position measurement
Social networking (online)
subgraph retrieval
Training
ISSN:1041-4347, 1558-2191
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Subgraph matching is challenging as it necessitates time-consuming combinatorial searches. Recent Graph Neural Network (GNN)-based approaches address this issue by employing GNN encoders to extract graph information and hinge distance measures to ensure containment constraints in the embedding space. These methods significantly shorten the response time, making them promising solutions for subgraph retrieval. However, they suffer from scale differences between graph pairs during encoding, as they focus on feature counts but overlook the relative positions of features within node-rooted subtrees, leading to disturbed containment constraints and false predictions. Additionally, their hinge distance measures lack discriminative power for matched graph pairs, hindering ranking applications. We propose NC-Iso, a novel GNN architecture for neural subgraph matching. NC-Iso preserves the relative positions of features by building the hierarchical dependencies between adjacent echelons within node-rooted subtrees, ensuring matched graph pairs maintain consistent hierarchies while complying with containment constraints in feature counts. To enhance the ranking ability for matched pairs, we introduce a novel similarity dominance ratio-enhanced measure, which quantifies the dominance of similarity over dissimilarity between graph pairs. Empirical results on nine datasets validate the effectiveness, generalization ability, scalability, and transferability of NC-Iso while maintaining time efficiency, offering a more discriminative neural subgraph matching solution for subgraph retrieval.
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2025.3583003