SimGNN: A Neural Network Approach to Fast Graph Similarity Computation

By Yunsheng Bai, Haoyang Ding, Song Bian, Ting-Li Chen, Yizhou Sun, Wei Wang. 2018

409 citations recorded by the source corpus.

Graph similarity search is among the most important graph-based applications, e.g. finding the chemical compounds that are most similar to a query compound. Graph similarity/distance computation, such as Graph Edit Distance (GED) and Maximum Common Subgraph (MCS), is the core operation of graph similarity search and many other applications, but very costly to compute in practice. Inspired by the recent success of neural network approaches to several graph applications, such as node or graph classification, we propose a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance. The proposed approach, called SimGNN, combines two strategies. First, we design a learnable embedding function that maps every graph into an embedding vector, which provides a global summary of a graph. A novel attention mechanism is proposed to emphasize the important nodes with respect to a specific similarity metric. Second, we design a pairwise node comparison method to supplement the graph-level embeddings with fine-grained node-level information. Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs. Taking GED computation as an example, experimental results on three real graph datasets demonstrate the effectiveness and efficiency of our approach. Specifically, our model achieves smaller error rate and great time reduction compared against a series of baselines, including several approximation algorithms on GED computation, and many existing graph neural network based models. Our study suggests SimGNN provides a new direction for future research on graph similarity computation and graph similarity search.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

Citations in the corpus

Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity (2019, methodology): “, 2018) and graph similarity/distance computation (Bai et al., 2019).”
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity (2019, methodology): “…learning with success in not only node-level tasks such as node classification [Kipf and Welling, 2016a] and link prediction [Zhang and Chen, 2018], but also graphlevel tasks such as graph classification [Ying et al., 2018] and graph similarity/distance computation [Bai et al., 2019].”
Parameter Prediction for Unseen Deep Architectures (2021, methodology): “It is used as an efﬁcient approximation of the exact graph distance algorithms [106, 107], which are infeasible for graphs of the size we consider here.”