Lecture 3 Additional Software Tools

• Python:
  • aequitas
  • AIF360
  • Algorithmic Fairness
  • fairlearn
  • fairml
  • solas-ai-disparity
  • tensorflow/fairness-indicators
  • Themis
• R:
  • AIF360
  • fairmodels
  • fairness

Lecture 3 Additional Software Examples

• Increase Fairness in Your Machine Learning Project with Disparate Impact Analysis using Python and H2O
• Testing a Constrained Model for Discrimination and Remediating Discovered Discrimination
• Machine Learning for High-risk Applications: Use Cases (Chapter 10)

Lecture 3 Additional Reading

• Introduction and Background:
  • 50 Years of Test (Un)fairness: Lessons for Machine Learning
  • Fairness and Machine Learning - Introduction
  • NIST SP1270: Towards a Standard for Identifying and Managing Bias in Artificial Intelligence
  • Fairness Through Awareness
• Discrimination Testing and Remediation Techniques:
  • An Empirical Comparison of Bias Reduction Methods on Real-World Problems in High-Stakes Policy Settings
  • Certifying and Removing Disparate Impact
  • Data Preprocessing Techniques for Classification Without Discrimination
  • Decision Theory for Discrimination-aware Classification
  • Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification Without Disparate Mistreatment
  • Learning Fair Representations
  • Mitigating Unwanted Biases with Adversarial Learning