API to interface with the GraphLog Dataset. GraphLog is a multi-purpose, multi-relational graph dataset built using rules grounded in first-order logic.
Homepage | Paper | API Docs | Dataset
- Core Generator logic of GraphLog is now released in its own repository, GLC! This repository will contain the specific instantiations of GLC which can be used to create various setups of GraphLog. Stay tuned for more updates!
- Supported Python Version: 3.6, 3.7, 3.8
- Install PyTorch from https://pytorch.org/get-started/locally/
- Install pytorch-geometric (and other dependencies) from https://github.com/rusty1s/pytorch_geometric#installation. Make sure that cpu/cuda versions for pytorch and pytorch-geometric etc matches.
pip install graphlog
Check out the notebooks on Basic Usage and Advanced Usage to quickly start playing with GraphLog.
pip install -e ".[dev]"- Install pre-commit hooks
pre-commit install - The code is linted using:
blackflake8mypy
- All the tests can be run locally using
nox
Code for experiments used in our paper are available in experiments/ folder.
- If you have questions, open an Issue
- If you have any questions or topics related to this project to discuss, please contact
koustuvs[at]meta.com.
Please open a Pull Request (PR).
If our work is useful for your research, consider citing it using the following bibtex:
@article{sinha2020graphlog,
Author = {Koustuv Sinha and Shagun Sodhani and Joelle Pineau and William L. Hamilton},
Title = {Evaluating Logical Generalization in Graph Neural Networks},
Year = {2020},
arxiv = {https://arxiv.org/abs/2003.06560}
}
CC-BY-NC 4.0 (Attr Non-Commercial Inter.)