yuji-roh/fairbatch

FairBatch: Batch Selection for Model Fairness (ICLR 2021)

29
/ 100
Experimental

This project helps machine learning engineers ensure their predictive models are fair, preventing bias against specific demographic groups. It takes an existing machine learning model and training data, and outputs a refined model that exhibits fairer predictions across different groups, measured by metrics like equal opportunity or demographic parity. Data scientists and ML engineers concerned with ethical AI and regulatory compliance would use this to improve model fairness without complex system overhauls.

No commits in the last 6 months.

Use this if you need to improve the fairness of your machine learning models to prevent demographic disparities, especially when you want to make minimal changes to your existing training setup.

Not ideal if you are looking for a tool to develop a new machine learning model from scratch or for tasks unrelated to mitigating algorithmic bias.

algorithmic-fairness ethical-ai bias-mitigation machine-learning-engineering model-governance
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

19

Forks

5

Language

Python

License

Last pushed

May 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuji-roh/fairbatch"

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