We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs. As the core operation of graph similarity search, pairwise graph similarity computation is a challenging problem due to the NP-hard nature of computing many graph distance/similarity metrics. We demonstrate our model using the Graph Edit Distance (GED) as the example metric. Experiments on three real graph datasets demonstrate that our model achieves the state-of-the-art performance on graph similarity search.
@article{arxiv.1810.10866,
title = {Convolutional Set Matching for Graph Similarity},
author = {Yunsheng Bai and Hao Ding and Yizhou Sun and Wei Wang},
journal= {arXiv preprint arXiv:1810.10866},
year = {2018}
}
Comments
NIPS 2018 Workshop: Relational Representation Learning. Note: Substantial text overlap with arXiv:1809.04440