Neural Network Graph Similarity Computation Based on Graph Fusion

--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. I NTRODUCTION Applications based on graph data structures, such as social network analysis [1], bioinformatics [2], and recommendation systems [3], play a crucial role in both academia and industry. Among them, graph similarity learning is one of the most significant challenges in graph-related machine learning tasks.