Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Aequitas Flow: Streamlining Fair ML Experimentation

Sérgio Jesus, Pedro Saleiro, Inês Oliveira e Silva, Beatriz M. Jorge, Rita P. Ribeiro, João Gama, Pedro Bizarro, Rayid Ghani

TL;DR

The Aequitas Flow module provides a pipeline for fairness-aware model training, hyperparameter optimization, and evaluation, enabling easy-to-use and rapid experiments and analysis of results.

Abstract

Aequitas Flow is an open-source framework and toolkit for end-to-end Fair Machine Learning (ML) experimentation, and benchmarking in Python. This package fills integration gaps that exist in other fair ML packages. In addition to the existing audit capabilities in Aequitas, the Aequitas Flow module provides a pipeline for fairness-aware model training, hyperparameter optimization, and evaluation, enabling easy-to-use and rapid experiments and analysis of results. Aimed at ML practitioners and researchers, the framework offers implementations of methods, datasets, metrics, and standard interfaces for these components to improve extensibility. By facilitating the development of fair ML practices, Aequitas Flow hopes to enhance the incorporation of fairness concepts in AI systems making AI systems more robust and fair.

Aequitas Flow: Streamlining Fair ML Experimentation

TL;DR

The Aequitas Flow module provides a pipeline for fairness-aware model training, hyperparameter optimization, and evaluation, enabling easy-to-use and rapid experiments and analysis of results.

Abstract

Aequitas Flow is an open-source framework and toolkit for end-to-end Fair Machine Learning (ML) experimentation, and benchmarking in Python. This package fills integration gaps that exist in other fair ML packages. In addition to the existing audit capabilities in Aequitas, the Aequitas Flow module provides a pipeline for fairness-aware model training, hyperparameter optimization, and evaluation, enabling easy-to-use and rapid experiments and analysis of results. Aimed at ML practitioners and researchers, the framework offers implementations of methods, datasets, metrics, and standard interfaces for these components to improve extensibility. By facilitating the development of fair ML practices, Aequitas Flow hopes to enhance the incorporation of fairness concepts in AI systems making AI systems more robust and fair.
Paper Structure (9 sections, 2 figures, 1 table)

This paper contains 9 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Aequitas Flow
  3. Experiment:
  4. Optimizer:
  5. Datasets:
  6. Methods:
  7. Audit:
  8. Plotting:
  9. Conclusion

Figures (2)

  • Figure 1: Diagram of an Experiment in Aequitas Flow. The user input is passed to the Experiment, which will instantiate the components (Methods, Datasets, and Optimizer) in the pipeline. For each target task (for a researcher or practitioner), different plotting methods can be used to analyze the experimental results.
  • Figure 2: Plots introduced in Aequitas Flow. Plot (a) is designed for model selection; Plot (b) compares the different tested methods.