GraRep

Source Code of GraRep version 1.0

Notice

1. You do not need impose L2 norm for embeddings again, or accuracy will be hurt. Actually normlization has been already done;
2. GraRep is suitable for undirected graph. If you want apply it for directed graph, please use matrix addition between adjacency matrix and its transpose to replace original adjaceny matrix before you run GraRep.

Lisence

This code follows the MIT Lisence.

GPU Version

This is a fast re-implemented versioin GraRep.jl using Julia language by xgfs.

Cite

If you want to use this code, please kinkdly cite our paper

@inproceedings{cao2015grarep,
title={Grarep: Learning graph representations with global structural information},
author={Cao, Shaosheng and Lu, Wei and Xu, Qiongkai},
booktitle={Proceedings of the 24th ACM International on Conference on Information and Knowledge Management},
pages={891--900},
year={2015},
organization={ACM}
}