Abstract
Computing the similarity between graphs is a longstanding and challenging problem with many real-world applications. Recent years have witnessed a rapid increase in neural-network-based methods, which project graphs into embedding space and devise end-to-end frameworks to learn to estimate graph similarity. Nevertheless, these solutions usually design complicated networks to capture the fine-grained interactions between graphs, and hence have low efficiency. Additionally, they rely on labeled data for training the neural networks and overlook the useful information hidden in the graphs themselves. To address the aforementioned issues, in this work, we put forward a contrastive neural graph similarity learning framework, Conga. Specifically, we utilize vanilla graph convolutional networks to generate the graph representations and capture the cross-graph interactions via a simple multilayer perceptron. We further devise an unsupervised contrastive loss to discriminate the graph embeddings and guide the training process by learning more expressive entity representations. Extensive experiment results on public datasets validate that our proposal has more robust performance and higher efficiency compared with state-of-the-art methods.
Funder
National Natural Science Foundation of China
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference51 articles.
1. Similarity Search in Biological and Engineering Databases;Kriegel;IEEE Data Eng. Bull.,2004
2. Heterogeneous Graph Matching Networks for Unknown Malware Detection;Wang;Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019,2019
3. Reinforcement Learning–based Collective Entity Alignment with Adaptive Features
4. Towards Entity Alignment in the Open World: An Unsupervised Approach;Zeng;Proceedings of the Database Systems for Advanced Applications—26th International Conference, DASFAA 2021,2021
5. On a relation between graph edit distance and maximum common subgraph