Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/google-research/smore
https://github.com/google-research/smore
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/google-research/smore
- Owner: google-research
- License: apache-2.0
- Created: 2021-09-23T21:03:50.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2022-12-08T02:09:57.000Z (about 2 years ago)
- Last Synced: 2024-11-07T10:41:23.575Z (about 1 month ago)
- Language: Python
- Size: 345 KB
- Stars: 162
- Watchers: 7
- Forks: 28
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
- awesome-logical-query - SMORE
- StarryDivineSky - google-research/smore
README
# SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
SMORE is a a versatile framework that scales multi-hop query embeddings over KGs. SMORE can easily train query embeddings on Freebase KG with more than 86M nodes and 338M edges on a single machine. For more details, please refer to our [paper](https://arxiv.org/pdf/2110.14890.pdf).
## Overview
![](https://github.com/google-research/smore/blob/main/assets/pipeline.png?raw=true)
SMORE designs an optimized pipeline with the following features.
- [x] Multi-GPU Training
- [x] Bidirectional Online Query Sampling## Installation
First clone the repository, and install the package dependency required in the `requirements.txt`.
Then navigate to the root folder of the project and do
git submodule update --init
pip install -e .## Models
SMORE supports six different singel / multi-hop reasoning methods on KG.
- [x] [BetaE](https://arxiv.org/abs/2010.11465)
- [x] [Query2box](https://arxiv.org/abs/2002.05969)
- [x] [GQE](https://arxiv.org/abs/1806.01445)
- [x] [RotatE](https://arxiv.org/abs/1902.10197)
- [x] [ComplEx](https://arxiv.org/abs/1606.06357)
- [x] [DistMult](https://arxiv.org/abs/1412.6575)## Examples
Please see the example script of each methods under `smore/training` folder. We provide example scripts of the six query emebddings on six KGs.
## Contributing
We welcome pull request, please check [CONTRIBUTING.md](https://github.com/Hanjun-Dai/multihop_kg/blob/license/CONTRIBUTING.md) for more details.
## Citations
If you use this repo, please cite the following paper.
```
@misc{ren2021smore,
title={SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs},
author={Hongyu Ren and Hanjun Dai and Bo Dai and Xinyun Chen and Denny Zhou and Jure Leskovec and Dale Schuurmans},
year={2021},
eprint={2110.14890},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```## License
SMORE is licensed under the Apache License, Version 2.0.This is not an officially supported Google product.
Contact [email protected] and [email protected] for questions about the repo.