Neural Network Graph Similarity Computation Based on Graph Fusion
This work addresses graph similarity computation for tasks like classification and search, offering a novel method that improves efficiency and accuracy, though it is incremental in advancing existing approaches.
The paper tackles the challenge of graph similarity learning by introducing a graph fusion method that merges node sequences into a single graph, enabling efficient interaction computations; extensive testing on five datasets shows it outperforms leading baselines in classification and regression tasks, setting new benchmarks for performance and efficiency.
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