benedekrozemberczki/SimGNN
A PyTorch implementation of SimGNN, a neural network approach for fast graph similarity computation using graph neural networks and attention mechanisms.
Velocity · 7d
+0.3
★ / day
Trend
→steady
star history
This repository provides a PyTorch implementation of the SimGNN paper from WSDM 2019. It combines learnable graph embedding functions with novel attention mechanisms to approximate Graph Edit Distance (GED) efficiently. The approach maps graphs into embedding vectors and uses a tensor network layer to compute similarity scores between graph pairs.