TimeLovercc/CAF-GNN

[CIKM 2023] Towards Fair Graph Neural Networks via Graph Counterfactual.

36
/ 100
Emerging

This project helps machine learning practitioners identify and reduce bias in classification decisions made by graph neural networks. It takes your existing graph-structured data and trained models, and outputs a refined model that makes fairer predictions. Anyone working with sensitive data like credit applications or loan approvals, where fairness and preventing discrimination are critical, would find this useful.

No commits in the last 6 months.

Use this if you need to ensure that your graph neural network models make fair, unbiased predictions on sensitive data, such as credit scores or bail risk, and you are comfortable with Python and PyTorch.

Not ideal if you are looking for a plug-and-play solution without any coding or if you are not familiar with machine learning development environments.

ethical-AI fairness-in-ML credit-scoring risk-assessment biased-decision-making
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

14

Forks

5

Language

Python

License

MIT

Last pushed

Mar 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TimeLovercc/CAF-GNN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.