PyGCL

PyGCL is a PyTorch-based open-source Graph Contrastive Learning (GCL) library, which features modularized GCL components from published papers, standardized evaluation, and experiment management.

Quickstart Read Docs

Installation

To install PyGCL with pip, simply run:

pip install PyGCL

Then, you can import GCL from your current environment.

Prerequisites

  • Python 3.8+
  • PyTorch 1.9+
  • PyTorch-Geometric 2.0+
  • DGL 0.7+
  • Scikit-learn 0.24+
  • Numpy
  • tqdm
  • NetworkX

Modularized Design

PyGCL features modularized design with four critical components of graph contrastive learning, which can be independently used or integrated into existing implementations.

Open Source

PyGCL is licensed under the Apache License 2.0 and actively maintained by the community on GitHub.

Wide Coverage

PyGCL covers a wide range of up-to-date models that are representative in open literature. It can also be easily extended to include more design choices.