AI Rank
中文
← Open Source
hwwang55

GraphGAN

A tensorflow implementation of GraphGAN (Graph Representation Learning with Generative Adversarial Nets).

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
538
Stars
156
Forks
+1
This week
3
Contributors
Created 2017-11-19 · Updated 2026-10-13 · #17460 today
Top developers
hwwang55wangjialin114suanrong

hwwang55/GraphGAN is ranked 17,460 with 538 stars.

Same-category comparison

hwwang55/GraphGAN is ranked 17,460 among these 8 peers; mlfoundations/open_lm is ranked 17,463.

Same-category comparison
NameRankMetrics
fancompute/wavetorch17,442
Language:
Python
Stars:
539
Forks:
85
Description:
🌊 Numerically solving and backpropagating through the wave equation.
wl-zhao/VPD17,451
Language:
Jupyter Notebook
Stars:
539
Forks:
33
Description:
[ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.
JDAI-CV/CoTNet17,453
Language:
Python
Stars:
538
Forks:
83
Description:
This is an official implementation for "Contextual Transformer Networks for Visual Recognition".
LucasAlegre/morl-baselines17,454
Language:
Python
Stars:
538
Forks:
110
Description:
Multi-Objective Reinforcement Learning algorithms implementations.
mlfoundations/open_lm17,463
Language:
Python
Stars:
538
Forks:
80
Description:
A repository for research on medium sized language models.
swarm-subnet/Langostino17,465
Language:
Python
Stars:
538
Forks:
82
Description:
Langostino - An open-source autonomous drone platform using ROS2 and AI-powered flight control. A complete reference implementation for building, understanding, and extending real-world drone autonomy.
ChenHongruixuan/ChangeDetectionRepository17,466
Language:
Python
Stars:
537
Forks:
108
Description:
This repository contains some python code of some traditional change detection methods or provides their original websites, such as SFA, MAD, and some deep learning-based change detection methods, such as SiamCRNN, DSFA, and some FCN-based methods.
Yonghongwei/Gradient-Centralization17,470
Language:
Python
Stars:
537
Forks:
81
Description:
A New Optimization Technique for Deep Neural Networks.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryArchitecture
KeywordsGraph neural networks
Stars538
Forks156
Contributors3
Created date2017-11-19
Updated date2026-10-13
Stars in 1 day0
Stars in 7 days1
Rank17,460
Previous rank17,246
Rank change-214
7-day stars rank11,439
Previous 7-day stars rank11,498
7-day stars rank change59
Total stars rank18,282
Previous total stars rank18,255
Total stars rank change-27
CountryUSA
README summary

GraphGAN This repository is the implementation of GraphGAN (arXiv): GraphGAN: Graph Representation Learning With Generative Adversarial Nets Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, Minyi Guo 32nd AAAI Conference on Artificial Intelligence, 2018 GraphGAN unifies two schools of graph representation learning methodologies: generative methods and discriminative methods, via adversarial training in a minimax game. The generator is guided by the signals from the discriminator and improves its generating performance, while the discriminator is

pushed by the generator to better distinguish ground truth from generated samples. Files in the folder : training and test data : pre-trained node embeddings Note: the dimension of pre-trained node embeddings should equal n_emb in src/GraphGAN/config. py : evaluation results and the learned embeddings of the generator and the discriminator : source codes Requirements The code has been tested running under Python 3. 5, with the following packages installed (along with their dependencies): tensorflow == 1. 4 (for displaying

the progress bar) numpy == 1. 1 Input format The input data should be an undirected graph in which node IDs start from *0* to *N-1* (*N* is the number of nodes in the graph). Each line contains two node IDs indicating an edge in the graph.

Frequently asked questions

How many stars and forks are recorded?

hwwang55/GraphGAN has 538 stars and 156 forks.

What is the repository rank?

hwwang55/GraphGAN is ranked 17,460.

What language and category are recorded?

hwwang55/GraphGAN has 538 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

hwwang55/GraphGAN is compared with mlfoundations/open_lm, ranked 17,463 with 538 stars.

README

GraphGAN

GraphGAN: Graph Representation Learning With Generative Adversarial Nets
Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, Minyi Guo
32nd AAAI Conference on Artificial Intelligence, 2018

GraphGAN unifies two schools of graph representation learning methodologies: generative methods and discriminative methods, via adversarial training in a minimax game. The generator is guided by the signals from the discriminator and improves its generating performance, while the discriminator is pushed by the generator to better distinguish ground truth from generated samples.

Files in the folder

  • data/: training and test data
  • pre_train/: pre-trained node embeddings

    Note: the dimension of pre-trained node embeddings should equal n_emb in src/GraphGAN/config.py

  • results/: evaluation results and the learned embeddings of the generator and the discriminator
  • src/: source codes

Requirements

The code has been tested running under Python 3.6.5, with the following packages installed (along with their dependencies):

  • tensorflow == 1.8.0
  • tqdm == 4.23.4 (for displaying the progress bar)
  • numpy == 1.14.3
  • sklearn == 0.19.1

Input format

The input data should be an undirected graph in which node IDs start from 0 to N-1 (N is the number of nodes in the graph). Each line contains two node IDs indicating an edge in the graph.

txt file sample

0 1
3 2
...

Basic usage

mkdir cache
cd src/GraphGAN
python graph_gan.py

Nearby in the ranking
Similar items