There are 2 repositories under algorithmic-fairness topic.
[Official Codes] Experiments on Generalizability of User-Oriented Fairness in Recommender Systems (SIGIR 2022)
[Nature Medicine] The Limits of Fair Medical Imaging AI In Real-World Generalization
Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency
Source code and models for the paper "Cyberbullying Detection with Fairness Constraints". IEEE Internet Computing, 2020
Python library with the core algorithms used to do FA*IR ranking.
Demographic Bias of Vision-Language Foundation Models in Medical Imaging
Fair search elasticsearch plugin
A School for All Seasons on Trustworthy Machine Learning
Analyzing Adversarial Bias and the Robustness of Fair Machine Learning
Disparate Exposure in Learning To Rank for Python
Code implementation for BiasMitigationRL, a reinforcement learning-based bias mitigation method.
Implementation of debiasing algorithm in "Debiasing Representations by Removing Unwanted Variation Due to Protected Attributes" on ProPublica's COMPAS data set
Disparate Exposure in Learning To Rank for Java
:pencil: Exploring the gradual (in)compatibility of the fairness metrics independence, separation and sufficiency.
Base on deep learning implementation of collaborative filtering, enhance fairness in terms of closing performance gap across users from different subgroups of gender and age
Trustworthy AI/ML course by Professor Birhanu Eshete, University of Michigan, Dearborn.
This project aims to understand the algorithmic bias in the corrections system through analyzing the COMPAS dataset.
Core algorithms used to do fair search. This algorithm are exposed through the Elasticsearch and Solr plugins.
:pencil: Implementation of our approach for balancing the utility of the decision maker and the fairness towards the decision subjects for a prediction-based decision-making system
Implementation of Joint Fairness Model with Applications to Risk Predictions for Under-represented Populations
Deliverables relating to the Ethics in Artificial Intelligence & Intelligent Interfaces University Units
A super-quick demo to start discussions on bias in Finnish BERT language model
Exercise repository for Algorithmic Fairness, Accountability and Ethics (Spring 2022), IT University of Copenhagen
Official Implementation of the paper "Fair Generalized Linear Models with a Convex Penalty."
Fairness in Digital Image Forgery Detection System
Colorful Bias is a longitudinal benchmarking of algorithmic colorization of images containing human skin tones.
:pencil: Exploring data-driven affirmative action policies for university admissions