Embedding Node Structural Role Identity into Hyperbolic Space

Requirements:

environment.yml

How to use

evaluate_nc.sh node classification experiments on Brazilian, American and European air-traffic network

vis_karate.sh embeddings visualization on karate network

vis_barbell.sh embeddings visualization on barbell graph

Data

We use the data provide from https://github.com/leoribeiro/struc2vec in our data directory

Code reference

McDonald, D., He, S.: Heat: Hyperbolic embedding of attributed networks. arXivpreprint arXiv:1903.03036 (2019)

struc2vec: Learning Node Representations from Structural Identity. Leonardo F. R. Ribeiro, Pedro H. P. Saverese, Daniel R. Figueiredo. Knowledge Discovery and Data Mining, SigKDD, 2017.

https://github.com/shenweichen/GraphEmbedding

Citation

If you find this useful, please use the following citation

@inproceedings{wang2020embedding,
  title={Embedding Node Structural Role Identity into Hyperbolic Space},
  author={Wang, Lili and Lu, Ying and Huang, Chenghan and Vosoughi, Soroush},
  booktitle={Proceedings of the 29th ACM International Conference on Information \& Knowledge Management},
  pages={2253--2256},
  year={2020}
}