Skip to content

upkarlidder/aifairness360-01.15.2020

master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 

Online Meetup: Removing Unfair Bias in Machine Learning

Important Links

Replay

Slides

AI Fairness 360

Links from slides

Papers on metrics and mitigation techniques

  • Optimized Preprocessing (Calmon et al., NIPS 2017)
  • Meta-Algorithm for Fair Classification (Celis et al., FAT* 2019)
  • Disparate Impact Remover (Feldman et al., KDD 2015)
  • Equalized Odds Postprocessing (Hardt et al., NIPS 2016)
  • Reweighing (Kamiran and Calders, KIS 2012)
  • Reject Option Classification (Kamiran et al., ICDM 2012)
  • Prejudice Remover Regularizer (Kamishima et al., ECML PKDD 2012)
  • Calibrated Equalized Odds Postprocessing (Pleiss et al., NIPS 2017)
  • Learning Fair Representations (Zemel et al., ICML 2013)
  • Adversarial Debiasing (Zhang et al., AIES 2018)

Abstract

Extensive evidence has shown that AI can embed human and societal bias and deploy them at scale. And many algorithms are now being reexamined due to illegal bias. So how do you remove bias & discrimination in the machine learning pipeline? In this talk you'll learn the debiasing techniques that can be implemented by using the open source toolkit AI Fairness 360.

AI Fairness 360 (AIF360) is an extensible, open source toolkit for measuring, understanding, and removing AI bias. AIF360 is the first solution that brings together the most widely used bias metrics, bias mitigation algorithms, and metric explainers from the top AI fairness researchers across industry & academia.

In this talk you'll learn:

  • How to measure bias in your data sets & models
  • How to apply the fairness algorithms to reduce bias
  • An introductory look at how bias & discrimination can arise within modern machine learning techniques and the methods that can be implemented to tackle those challenges.
  • Learn how to evaluate the metrics using the open-source AI Fairness 360 Toolkit to check for fairness and mitigate machine learning model bias.

Replay - https://www.crowdcast.io/e/removing-unfair-bias-in

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published