SEGMN: A Structure-Enhanced Graph Matching Network for Graph Similarity Learning

TL;DR

SEGMN introduces a novel graph neural network that enhances node embeddings with structural information and employs a structure perception module for improved graph similarity measurement, outperforming existing methods.

Contribution

The paper proposes SEGMN, a structure-enhanced graph matching network that incorporates edge information into node embeddings and uses a structure perception module for better cross-graph matching.

Findings

Outperforms state-of-the-art GSC methods on benchmark datasets.

Structure perception matching module improves baseline performance by up to 25%.

Achieves better accuracy in GED regression tasks.

Abstract

Graph similarity computation (GSC) aims to quantify the similarity score between two graphs. Although recent GSC methods based on graph neural networks (GNNs) take advantage of intra-graph structures in message passing, few of them fully utilize the structures presented by edges to boost the representation of their connected nodes. Moreover, previous cross-graph node embedding matching lacks the perception of the overall structure of the graph pair, due to the fact that the node representations from GNNs are confined to the intra-graph structure, causing the unreasonable similarity score. Intuitively, the cross-graph structure represented in the assignment graph is helpful to rectify the inappropriate matching. Therefore, we propose a structure-enhanced graph matching network (SEGMN). Equipped with a dual embedding learning module and a structure perception matching module, SEGMN achieves structure enhancement in both embedding learning and cross-graph matching. The dual embedding learning module incorporates adjacent edge representation into each node to achieve a structure-enhanced representation. The structure perception matching module achieves cross-graph structure enhancement through assignment graph convolution. The similarity score of each cross-graph node pair can be rectified by aggregating messages from structurally relevant node pairs. Experimental results on benchmark datasets demonstrate that SEGMN outperforms the state-of-the-art GSC methods in the GED regression task, and the structure perception matching module is plug-and-play, which can further improve the performance of the baselines by up to 25%.