Graph Matching Networks

This is a reimplementation of the ICLR 2019 paper Graph Matching Networks for Learning the Similarity of Graph Structured Objects (Li et al.) in PyTorch.

Note: I'm not one of the original authors.

Requirements

• torch >= 1.6.0
• torch_geometric (Installation guide)

Instructions

• Install the requirements
• Import the models from models.py

References:

• Official Colab notebook (using TensorFlow 1.0 and Sonnet)
• A repo that adaps the official notebook to python files