Home

Awesome

Unsupervised Network Embedding Beyond Homophily

(also named as: Unsupervised Heterophilous Network Embedding via r-Ego Network Discrimination)

Implementation of Selene with Pytorch.

Required packages

The code has been tested running under Python 3.9.6. with the following packages installed (along with their dependencies):

Data requirement

All eight datasets we used in the paper are all public datasets which can be downloaded from the internet.

Code execution

python main.py --data_name Texas --layer_num 2 --epoch_num 501 --lr 0.01 --p_x 0.2 --p_e 0.3 --gnn_encoder GCN --feat_method rw --SEED 1234 --gpu True

Cite

Please cite our paper if it is helpful in your own work:

@article{ZGGP22,
title = {Unsupervised Network Embedding Beyond Homophily},
author = {Zhiqiang Zhong and Guadalupe Gonzalez and Daniele Grattarola and Jun Pang},
journal = {Transactions on Machine Learning Research (TMLR)},
year = {2022},
}