hyren / query2box

Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings

Home Page:http://snap.stanford.edu/query2box

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Query2box

A new and more modularized implementation can be found at here

Official implementation of Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings.

Hongyu Ren*, Weihua Hu*, Jure Leskovec, ICLR 2020.

Requirements

torch==1.2.0
tensorboadX==1.6

Run

To reproduce the results on FB15k, FB15k-237 and NELL, the hyperparameters are set in example.sh.

bash example.sh

Cite

Please consider cite our paper if you find the paper and the code useful.

@inproceedings{ren2020query2box,
  title={Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings},
  author={Ren, Hongyu and Hu, Weihua and Leskovec, Jure},
  booktitle={International Conference on Learning Representations},
  year={2020},
  url={https://openreview.net/forum?id=BJgr4kSFDS},
}

Feel free to send email to hyren@cs.stanford.edu if you have any questions. This code also borrows from RotatE.

About

Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings

http://snap.stanford.edu/query2box

License:MIT License


Languages

Language:Python 98.9%Language:Shell 1.1%