Improving Subgraph Matching by Combining Algorithms and Graph Neural Networks

Abstract

Homomorphism is a key mapping technique between graphs that preserves their structure. Given a graph and a pattern, the subgraph homomorphism problem involves finding a mapping from the pattern to the graph, ensuring that adjacent vertices in the pattern are mapped to adjacent vertices in the graph. Unlike subgraph isomorphism, which requires a one-to-one mapping, homomorphism allows multiple vertices in the pattern to map to the same vertex in the graph, making it more complex. We propose HFrame, the first graph neural network-based framework for subgraph homomorphism, which integrates traditional algorithms with machine learning techniques. We demonstrate that HFrame outperforms standard graph neural networks by being able to distinguish more graph pairs where the pattern is not homomorphic to the graph. Additionally, we provide a generalization error bound for HFrame. Through experiments on both real-world and synthetic graphs, we show that HFrame is up to 101.91 times faster than exact matching algorithms and achieves an average accuracy of 0.962.

KDD 2025

References in corpus (8)

• Inductive Representation Learning on Large Graphs
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• A Survey of Graph Neural Networks for Social Recommender Systems
• Generalization and Representational Limits of Graph Neural Networks
• GuP: Fast Subgraph Matching by Guard-based Pruning
• How Powerful are K-hop Message Passing Graph Neural Networks
• On the expressive power of message-passing neural networks as global feature map transformers
• Weisfeiler and Leman Go Relational