Codebase for "Fair-GAIN" for fair ML predictions.

Resources related to Watson OpenScale

Examining the susceptibility of Fairness Measures to various scenarious of data imbalance

Hmumu classifiers trained to be fair w.r.t. the invariant mass.

Affevtive Bias in Large Pre-trained Language Models

🔍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. 👨🏽‍🔧

Fairness in Digital Image Forgery Detection System

The aim of the project is to apply different global, local and performance interpretability methods as well as model fairness evaluations to a dataset with protected attributes. The dataset regards traffic violations in Montgomery, Maryland, USA. This is a fork of a group project of my Data Science for Business Master's Degree at HEC Paris.

FACT-AI (Fairness, Accountability, Confidentiality, and Transparency in AI) Project on Debiasing word embeddings

[Official Codes] Exploring the Impact of Temporal Bias in Point-of-Interest Recommendation (RecSys 22)

Demos for my blog, Ponder @ ponder.substack.com

ChaiWithPy - the technical blog with a dash of tea

A collection of notebooks to explore bias, fairness and explainability of machine learning models

The GitHub repository for the reproducibility paper: Replication Study of "Fairness and Bias in Online Selection"

TrustyAI main documentation

Code and data for the paper "Correlation Clustering with Global Weight Bounds", ECML-PKDD 2021

Building Fair AI models tutorial at PyData Berlin / REVISION 2018

Report for INFO4900 Independent Research under Prof. Dawn Schrader. Surveyed bias detection and mitigation methods in language models. Identified emerging Language Model tasks where existing mechanisms fail. Designed a novel fairness test and proposed a framework to update large language models when what society considers fair changes.

This workflow is generated by Geoweaver to replicate the experiments done in EmissionAI's published article. Currently, the workflow retrieves the data from an already compiled source, but the next version will make this workflow collect data from the different data sources directly.