Skip to content

Latest commit

 

History

History
32 lines (26 loc) · 1.13 KB

README.md

File metadata and controls

32 lines (26 loc) · 1.13 KB

unsupervised-graph-embeddings

Code to test the semantic content of unsupervised graph embeddings.

  • get_features.py contains functions to extract features from graph using networkx ;
  • eval.py contains functions to evaluate pre-trained graph embeddings ;

Cite

Please cite the associated papers for this work if you use this code:

@inproceedings{bonner2017evaluating,
  title={Evaluating the quality of graph embeddings via topological feature reconstruction},
  author={Bonner, Stephen and Brennan, John and Kureshi, Ibad and Theodoropoulos, Georgios and McGough, Andrew Stephen and Obara, Boguslaw},
  booktitle={2017 IEEE International Conference on Big Data (Big Data)},
  pages={2691--2700},
  year={2017},
  organization={IEEE}
}

@article{bonner2019exploring,
  title={Exploring the Semantic Content of Unsupervised Graph Embeddings: An Empirical Study},
  author={Bonner, Stephen and Kureshi, Ibad and Brennan, John and Theodoropoulos, Georgios and McGough, Andrew Stephen and Obara, Boguslaw},
  journal={Data Science and Engineering},
  volume={4},
  number={3},
  pages={269--289},
  year={2019},
  publisher={Springer}
}