Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching

TL;DR

This paper introduces GraphSim, a neural network model that directly matches sets of node embeddings for more accurate graph similarity computation, outperforming existing methods on multiple datasets.

Contribution

It proposes a novel set-matching approach for graph similarity, overcoming limitations of fixed-dimensional graph embeddings used in prior neural methods.

Findings

Achieves state-of-the-art performance on four real-world datasets

Outperforms existing methods in six out of eight evaluation settings

Effectively captures fine-grained differences between graphs

Abstract

Graph similarity computation is one of the core operations in many graph-based applications, such as graph similarity search, graph database analysis, graph clustering, etc. Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed. Recently, several data-driven approaches based on neural networks have been proposed, most of which model the graph-graph similarity as the inner product of their graph-level representations, with different techniques proposed for generating one embedding per graph. However, using one fixed-dimensional embedding per graph may fail to fully capture graphs in varying sizes and link structures, a limitation that is especially problematic for the task of graph similarity computation, where the goal is to find the fine-grained difference between two graphs. In this paper, we address the problem of graph similarity computation from another perspective, by directly matching two sets of node embeddings without the need to use fixed-dimensional vectors to represent whole graphs for their similarity computation. The model, GraphSim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings (here we count a specific dataset and metric combination as one setting), compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.