English

Convolutional Set Matching for Graph Similarity

Machine Learning 2018-11-15 v3 Machine Learning

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-23T04:52:31.744Z