facebookresearch / Graphlog
Licence: other
API for accessing the GraphLog dataset
Stars: ✭ 82
Labels
Projects that are alternatives of or similar to Graphlog
Whatsapp Radiologist
A chatbot built in python using Selenium module.
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Continuous analysis
Computational reproducibility using Continuous Integration to produce verifiable end-to-end runs of scientific analysis.
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
2017 Ccf Bdci Enterprise
2017-CCF-BDCI-企业经营退出风险预测：9th/569 (Top 1.58%)
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Entailment With Tensorflow
Accompanying notebook for the Entailment with Tensorflow article.
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Ergo
A Python library for integrating model-based and judgmental forecasting
Stars: ✭ 82 (+0%)
Mutual labels: jupyter-notebook
Video2gif code
Video2GIF neural network model from our paper at CVPR2016
Stars: ✭ 80 (-2.44%)
Mutual labels: jupyter-notebook
Juliaopt Notebooks
A collection of IJulia notebooks related to optimization
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Summerschool2017
Material for the Montréal Deep Learning Summer School 2017
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Mad
Code for "Online and Linear Time Attention by Enforcing Monotonic Alignments"
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Caffe Spn
Codes for Learning Affinity via Spatial Propagation Networks
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Google It Automation
google it automation with python professional certificate
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Ai For Trading
code repository for Udacity nanodegree Artificial Intelligence for Trading
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Expo Mf
Exposure Matrix Factorization: modeling user exposure in recommendation
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
Jupyter to medium
Python package for publishing Jupyter Notebooks as Medium blogposts
Stars: ✭ 82 (+0%)
Mutual labels: jupyter-notebook
Mapidoc
Public repo for Materials API documentation
Stars: ✭ 81 (-1.22%)
Mutual labels: jupyter-notebook
GraphLog
API to interface with the GraphLog Dataset. GraphLog is a multi-purpose, multi-relational graph dataset built using rules grounded in first-order logic.
News
- 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!
Installation
- 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
QuickStart
Check out the notebooks on Basic Usage and Advanced Usage to quickly start playing with GraphLog.
Dev Setup
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
Experiments
Code for experiments used in our paper are available in experiments/ folder.
Questions
- If you have questions, open an Issue
- Or, join our Slack channel and post your questions / comments!
- To contribute, open a Pull Request (PR)
Contributing
Please open a Pull Request (PR).
Citation
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}
}
License
CC-BY-NC 4.0 (Attr Non-Commercial Inter.)
Terms of Use
https://opensource.facebook.com/legal/terms
Privacy Policy
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].