Neural Network Graph Similarity Computation Based on Graph Fusion

TL;DR

This paper introduces a novel graph fusion method for graph similarity learning that merges graph pairs into a single structure, enabling efficient global attention-based interaction and outperforming existing models.

Contribution

The paper proposes a parallel graph fusion approach that simplifies and accelerates graph similarity computation using global attention and dual-level similarity assessment.

Findings

Outperforms baseline models in classification and regression tasks

Sets new benchmarks in accuracy and efficiency

Demonstrates effectiveness across five public datasets

Abstract

Graph similarity learning, crucial for tasks such as graph classification and similarity search, focuses on measuring the similarity between two graph-structured entities. The core challenge in this field is effectively managing the interactions between graphs. Traditional methods often entail separate, redundant computations for each graph pair, leading to unnecessary complexity. This paper revolutionizes the approach by introducing a parallel graph interaction method called graph fusion. By merging the node sequences of graph pairs into a single large graph, our method leverages a global attention mechanism to facilitate interaction computations and to harvest cross-graph insights. We further assess the similarity between graph pairs at two distinct levels-graph-level and node-level-introducing two innovative, yet straightforward, similarity computation algorithms. Extensive testing across five public datasets shows that our model not only outperforms leading baseline models in graph-to-graph classification and regression tasks but also sets a new benchmark for performance and efficiency. The code for this paper is open-source and available at https://github.com/LLiRarry/GFM-code.git