bias-mitigation

visionjo/facerec-bias-bfw

Source code and notebooks to reproduce experiments and benchmarks on Bias Faces in the Wild (BFW).

oracle/guardian-ai

Oracle Guardian AI Open Source Project is a library consisting of tools to assess fairness/bias and privacy of machine learning models and data sets.

ashryaagr/Fairness.jl

Julia Toolkit with fairness metrics and bias mitigation algorithms

EqualityAI/EqualityML

Evidence-based tools and community collaboration to end algorithmic bias, one data scientist at a time.

zhihengli-UR/DebiAN

Official code of "Discover and Mitigate Unknown Biases with Debiasing Alternate Networks" (ECCV 2022)

arezou-pakzad/CIRCLe

CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions

YyzHarry/shortcut-ood-fairness

The Limits of Fair Medical Imaging AI In The Wild

YyzHarry/vlm-fairness

Demographic Bias of Vision-Language Foundation Models in Medical Imaging

Jiaxuan-Li/PnD

[ICCV 2023] Partition-and-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts

scotthlee/fairness

Enforcing fairness in binary and multiclass classification

aliciapj/xai-genz

Explainable AI & fashion talk & experiments

Wazzabeee/Bias-Mitigation-In-LLM

Research POC on the mitigation of bias in large language models (FLAN-T5 and Bloomz) through fine-tuning.

yangjenny/BiasMitigationRL

Code implementation for BiasMitigationRL, a reinforcement learning-based bias mitigation method.

sfu-mial/CIRCLe

CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions. Mirror of https://github.com/arezou-pakzad/CIRCLe

MarwanMashra/bias-mitigation-for-age-detection

An ML competition on CodaLab to estimate the age from images while mitigating the bias

meilfang/FairnessFacePAD

Fairness in Face Presentation Attack Detection

MIND-Lab/Debiasing-Misogynous-Meme-Recognition-Systems

3x-dev/ChatGPT-Political-Bias-Mitigation-ConstitutionalAI

Codebase for political bias mitigation in ChatGPT using Anthropic's ConstitutionalAI principles

boyla950/classification-with-no-discrimination

Coursework solutions for a 2nd year Computer Science sub-module on Bias in AI @ Durham University. Attempts to minimise gender bias when using ML to predict income.

imrehg/cdei-development

Machine Learning Bias Exploration

JohnOlushola/bias-mitigation

Mitigating algorithmic bias using regularisation and reweighing with bi-objective (accuracy and fairness) measure

Team-Obisidan/Biases-im-Machine-Learning

This German scientific poster (developed as HTML5/React web app) shows the potential implications of racial/social/... Biases in the context of Machine Learning

adastra21/fairness_aware_preprocessing

Explore how bias can be detected and mitigated in real-world datasets

CharmaineBarker/FairVIC

All the material needed to implement FairVIC for bias mitigation in deep neural networks.

gautamHCSCV/Bias-Mitigation-using-Knowledge-Distillation

A teacher model with minimal bias or calibrate its outputs to reduce bias transfer during distillation. Focus on distilling information from teacher features that are less prone to bias, like semantic representations instead of raw activations.

giordanoDaloisio/demv

Debiaser for Multiple Variables, a model- and data- agnostic method to improve fairness in binary and multi-class classification tasks

Innoccull/responsible_ai_demo

A demonstration of detecting and mitigating bias in AI.

rishabhpatel9/MSc-Final-Project

Gender classification model that uses a CNN to classify images of faces as male or female. The notebook includes code for data preprocessing, model architecture, training, and evaluation which will then be used for algorithmic bias detection.

ToineSayan/counterfactual-representations-for-explanation

Pytorch implementation of 'Explaining text classifiers with counterfactual representations'

upunaprosk/fair-pruning

Code for the paper The Other Side of Compression: Measuring Bias in Pruned Transformers (IDA23)

ghoshs/class_cardinality_comparison

Data and Results for WWW paper

hudson-newey/Bias-Alert

A small and simple prototype designed to alert users of the bias of the news source.

MajaMittag/gender_bias_da

Measure and mitigate gender bias in Danish toxicity classifiers and sentiment analysis models.

marcosdelcueto/MachineLearningLandscapes

The code generates simulated research landscapes of any given bias. It can be used to calculate the Machine Learning Gain under different conditions.