Efficient Graph Similarity Computation with Alignment Regularization

TL;DR

This paper introduces a novel regularization technique called Alignment Regularization (AReg) that enables efficient graph similarity computation using GNNs without expensive node-level matching, achieving high accuracy and speed.

Contribution

The paper proposes AReg, a simple regularization method that improves graph similarity estimation by eliminating the need for node-level matching, reducing computational costs.

Findings

AReg achieves comparable accuracy to state-of-the-art methods.

The approach significantly reduces training and inference time.

The method demonstrates strong transferability across datasets.

Abstract

We consider the graph similarity computation (GSC) task based on graph edit distance (GED) estimation. State-of-the-art methods treat GSC as a learning-based prediction task using Graph Neural Networks (GNNs). To capture fine-grained interactions between pair-wise graphs, these methods mostly contain a node-level matching module in the end-to-end learning pipeline, which causes high computational costs in both the training and inference stages. We show that the expensive node-to-node matching module is not necessary for GSC, and high-quality learning can be attained with a simple yet powerful regularization technique, which we call the Alignment Regularization (AReg). In the training stage, the AReg term imposes a node-graph correspondence constraint on the GNN encoder. In the inference stage, the graph-level representations learned by the GNN encoder are directly used to compute the similarity score without using AReg again to speed up inference. We further propose a multi-scale GED discriminator to enhance the expressive ability of the learned representations. Extensive experiments on real-world datasets demonstrate the effectiveness, efficiency and transferability of our approach.