Convolutional Set Matching for Graph Similarity

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.

NIPS 2018 Workshop: Relational Representation Learning. Note: Substantial text overlap with arXiv:1809.04440

References in corpus (2)

• Inductive Representation Learning on Large Graphs
• Variational Graph Auto-Encoders

Cited by in corpus (9)

• Deep Graph Matching Consensus
• GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
• Neural Subgraph Matching
• Exchangeable deep neural networks for set-to-set matching and learning
• Deep Graph Similarity Learning: A Survey
• IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification
• CoSimGNN: Towards Large-scale Graph Similarity Computation
• Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation
• A Statistical Relational Approach to Learning Distance-based GCNs