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 🔎🤖🧰

Official implementation of our work "Collaborative Fairness in Federated Learning."

Learning Fair Representations for Recommendation: A Graph-based Perspective, WWW2021

Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency

Paper lists about 'Constitutional AI System' or 'AI under Ethical Guidelines'

Official implementation of "FairEHR-CLP: Towards Fairness-Aware Clinical Predictions with Contrastive Learning in Multimodal Electronic Health Records" (MLHC 2024)

Fairness accountable regression in Matlab

implementation of fair dummies

Tensorflow constrained optimization with different Deep Learning Models

LLMs Prefix Tunning approach for hate speech detection

Package implementing methods developed in "Preventing Fairness Gerrymandering" [ICML '18], "Rich Subgroup Fairness for Machine Learning" [ FAT* '19]. active development fork @algowatchupenn

Fairness-aware Data Mining

Predicting student academic performance using machine learning, data analytics, and bias mitigation. The project analyzes how demographic, academic, and social factors affect grades while ensuring fairness across attributes like gender and past failures.

Mitigate machine learning bias to ensure data ethics in U.S. national home mortgage dataset.

Human in the Loop

Analyze borrower data and enhance decision-making for financial institutions, focusing on mitigating risks, ensuring fairness, and maintaining transparency and regulatory compliance.