This repository contains a custom extension of the GraphGym research library for Graph Neural Networks (GNNs) using PyTorch. The project aims to transform GraphGym into a more efficient and convenient predictive coding library.
Extends GraphGym, a research library for GNNs using PyTorch Implements predictive coding techniques for GNNs Optimizes performance and speeds up training and inference
Clone the PyTorch Geometric repository: bash Copy code
git clone https://github.com/pyg-team/pytorch_geometric.git
Replace the original GraphGym submodule with this custom module: bash Copy code
git clone https://github.com/yourusername/pc-graphgym-submodule.git pytorch_geometric/graphgym
Follow the instructions and examples provided in the PyTorch Geometric repository to utilize the extended GraphGym submodule in your GNN experiments.
Your contributions to improve and extend this custom module are greatly appreciated! Please submit issues and pull requests on the GitHub repository.