https://github.com/librahu/HeGAN

Source code for KDD 2019 paper "Adversarial Learning on Heterogeneous Information Networks"
https://github.com/librahu/HeGAN

Last synced: about 1 month ago
JSON representation

Source code for KDD 2019 paper "Adversarial Learning on Heterogeneous Information Networks"

• Host: GitHub
• URL: https://github.com/librahu/HeGAN
• Owner: librahu
• Created: 2019-02-12T08:25:30.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-05-05T09:34:38.000Z (over 5 years ago)
• Last Synced: 2024-08-01T22:41:47.717Z (4 months ago)
• Language: Python
• Homepage:
• Size: 14.2 MB
• Stars: 71
• Watchers: 2
• Forks: 24
• Open Issues: 8
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-network-embedding - [Python

README

        
# HeGAN

Source code for paper "Adversarial Learning on Heterogeneous Information Network (KDD2019)"

## Evironment Setting

* Python == 2.7.3

* Tensorflow == 1.12.0

* Numpy == 1.15.1

## Parameter Setting (see config.py)

batch_size : The size of batch.

lambda_gen, lambda_dis : The regularization for generator and discriminator, respectively.

lr_gen, lr_dis : The learning rate for generator and discriminator, respectively.

n_epoch : The maximum training epoch.

sig : The variance of gaussian distribution in generator. 

g_epoch, d_epoch: The number of generator and discriminator training per epoch.

n_sample : The size of sample

n_emb : The embedding size

## Files in the folder

* data/: The training data

* results/: The learned embeddings of generator ane discriminator.

* code/: The source codes

* pre_train/: The pre-trained node embeddings (Note: The dimension of pre-trained node embeddings should equal n_emb)

## Data 

We provide three datasets: [DBLP](https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/tree/master/DBLP), [Yelp](https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/tree/master/Yelp_2) and [Aminer](https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/tree/master/Aminer), The detailed description of the three datasets can refer to https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding

### The format of input training data

* Each line: source_node target_node relation

### The format of input pre-trained data

* The first line: node_num embedding_dim

* Each line : node_id embdeeing_1 embedding_2, ...

### The format of output embedding

* The first line: node_num embedding_dim

* Each line : node_id embdeeing_1 embedding_2, ...

## Basic Usage 

cd code

python he_gan.py

# Reference

@inproceedings{

> author = {Binbin Hu, Yuan Fang and Chuan Shi.},

 

> title = {Adversarial Learning on Heterogeneous Information Network},

 

> booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},

 

> year = {2019},

 

> publisher = {ACM},

> address = {Anchorage, Alaska, USA},

> year = {2019},

> keywords = {Heterogeneous Information Network, Network Embedding, Generative Adversarial Network},

 

}