Convolutional Set Matching for Graph Similarity
Published in
arXiv.org(2018)External Links:
TL
TL;DR
This work introduces GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs and demonstrates that the model achieves the state-of-the-art performance on graph similarity search.
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.
References35 items
1
On the exact computation of the graph edit distance
2
Learning Graph Distances with Message Passing Neural Networks
3
Deep Learning of Graph Matching
4
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
5