A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
-
Updated
Jul 5, 2024 - Python
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰
WEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
NeurIPS 2019 Paper: RUBi : Reducing Unimodal Biases for Visual Question Answering
Estimation and inference from generalized linear models using explicit and implicit methods for bias reduction
[ICML 2022] Channel Importance Matters in Few-shot Image Classification
Location-adjusted Wald statistics
Bias correction command-line tool for climatic research written in C++
unbiased toxicity detection from comments
Methods for M-estimation of statistical models
This repository contains the code to replicate the numerical studies presented in the paper "A Flexible Bias Correction Method based on Inconsistent Estimators".
Tensorflow implementation of Learning Not to Learn (CVPR 2019)
Pytorch implementation of 'Explaining text classifiers with counterfactual representations' (Lemberger & Saillenfest, 2024)
Critical questions to help you gain useful information, clarify the context, figure out the pain points, and overcome biases.
The repository contains software library for Data Augmentation Services
A method to preprocess the training data, producing an adjusted dataset that is independent of the group variable with minimum information loss.
A small and simple prototype designed to alert users of the bias of the news source.
Sampling algorithms and machine learning models to reduce bias and predict credit risk.
🔍In recent years the advancement of ML (machine learning) increased automation for tasks in different domains. One of the challanges was an issues with job recruitment systems that demonstrated bias toward female applicants [4]. This repo will investigate some of the techniques used to overcome these challenges. 👨🏽🔧
Bias reduction in quasi likelihood estimation
Add a description, image, and links to the bias-reduction topic page so that developers can more easily learn about it.
To associate your repository with the bias-reduction topic, visit your repo's landing page and select "manage topics."