AIF360 0.1.1 Release Notes

This update contains no feature changes.

Fixes

• changes to description for PyPI

AIF360 0.1.0 Release Notes

The AI Fairness 360 toolkit is an open-source library to help detect and remove bias in machine learning models. The AI Fairness 360 Python package includes a comprehensive set of metrics for datasets and models to test for biases, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

Highlights

A brief list of features provided in this release include:

• Algorithms:
  • Optimized Preprocessing (Calmon et al., 2017)
  • Disparate Impact Remover (Feldman et al., 2015)
  • Equalized Odds Postprocessing (Hardt et al., 2016)
  • Reweighing (Kamiran and Calders, 2012)
  • Reject Option Classification (Kamiran et al., 2012)
  • Prejudice Remover Regularizer (Kamishima et al., 2012)
  • Calibrated Equalized Odds Postprocessing (Pleiss et al., 2017)
  • Learning Fair Representations (Zemel et al., 2013)
  • Adversarial Debiasing (Zhang et al., 2018)
• Datasets Interface (raw data not included)
  • UCI ML Repository: Adult, German Credit, Bank Marketing
  • ProPublica Recidivism
  • Medical Expenditure Panel Survey
• Metrics
  • Comprehensive set of group fairness metrics derived from selection rates and error rates
  • Comprehensive set of sample distortion metrics
  • Generalized Entropy Index (Speicher et al., 2018)
• Metric Explanations
  • Text and JSON output formats supported