Attend the Women in ML Symposium on December 7 Register now

Module: model_remediation

Stay organized with collections Save and categorize content based on your preferences.

TensorFlow Model Remediation Library for addressing concerns in machine learning models.

The library contains a collection of techniques for addressing a wide range of concerns.

Current TensorFlow Model Remediation techniques:

  • MinDiff: Reduces performance gaps between example subgroups.
  • Counterfactual: Reduces the difference between two similar pairs.

Other Documentation:

Modules

counterfactual module: API for Counterfactual integration.

min_diff module: API for MinDiff integration.

version '0.1.7.1'