yuji-roh/fairbatch
FairBatch: Batch Selection for Model Fairness (ICLR 2021)
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.
Stars
19
Forks
5
Language
Python
License
—
Category
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.
Higher-rated alternatives
fairlearn/fairlearn
A Python package to assess and improve fairness of machine learning models.
Trusted-AI/AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations...
microsoft/responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment...
holistic-ai/holisticai
This is an open-source tool to assess and improve the trustworthiness of AI systems.
EFS-OpenSource/Thetis
Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines)...