Official implementation of GNNFairViz
Project description
GNNFairViz
Overview
GNNFairViz is a visualization tool designed to provide insights into the fairness of Graph Neural Networks from the perspective of data.
Installation
You can install GNNFairViz using pip or from source.
Using pip
pip install gnnfairviz
From Source
git clone https://github.com/xinwuye/GNNFairViz.git
cd GNNFairViz
pip install .
Usage
Examples of how to use the package can be found in the evaluation/cases
folder.
Features
- Support customizing and inspecting fairness through various viewpoints.
- Provide clues and interactions for node selection to analyze how they affect model bias.
- Allow diagnosing GNN fairness issues in an interactive manner.
Contributing
We welcome contributions! Follow these steps to set up your development environment and contribute to the project.
Setting Up the Development Environment
git clone https://github.com/xinwuye/GNNFairViz.git
cd GNNFairViz
poetry install
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contact
For questions or support, please contact:
- Email: xwye23@m.fudan.edu.cn
- GitHub Issues: GitHub Issues
Credits
This project uses and adapts code from the following repositories:
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file gnnfairviz-0.0.1.post1.tar.gz
.
File metadata
- Download URL: gnnfairviz-0.0.1.post1.tar.gz
- Upload date:
- Size: 1.4 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | aaa910ac94e03c0551a24f4f926007eb3be45829a14eb8429c07f1a6f057789b |
|
MD5 | 05eee127c94cb126d23f9b0f1db178c3 |
|
BLAKE2b-256 | e0db22ea607cfcc4e5bc1851d519856b894a19feceaf6aecc2de42429661bb3b |
File details
Details for the file gnnfairviz-0.0.1.post1-py3-none-any.whl
.
File metadata
- Download URL: gnnfairviz-0.0.1.post1-py3-none-any.whl
- Upload date:
- Size: 34.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0e983bffc27f5ad615448faafb5bb3932a4144d5a137d768210d45f028983dd7 |
|
MD5 | 490e5f6406570d93a4e8058b21d181b4 |
|
BLAKE2b-256 | 85bab2bb8ffeddafc4538a5b6d693365d978a2b769b38520f048728d4fb6ed27 |