# Convolutional Set Matching for Graph Similarity

arXiv: https://arxiv.org/abs/1810.10866 · HTML: https://mlsanity.com/paper/1810.10866/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2018.

## Built on by (most cited first, 7 of 7)

- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More](https://mlsanity.com/paper/2107.06876/) (2021)
- [Permute Me Softly: Learning Soft Permutations for Graph Representations](https://mlsanity.com/paper/2110.01872/) (2021)
- [SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts](https://mlsanity.com/paper/2108.12992/) (2021)
- [A Statistical Relational Approach to Learning Distance-based GCNs](https://mlsanity.com/paper/2102.07007/) (2021)
- [xNeuSM: Explainable Neural Subgraph Matching with Graph Learnable Multi-hop Attention Networks](https://mlsanity.com/paper/2312.01612/) (2023)

## Abstract (arXiv)

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.