FairPilot: An Explorative System for Hyperparameter Tuning through the Lens of Fairness

TL;DR

FairPilot is an interactive system that helps practitioners explore and select machine learning models based on multiple fairness criteria and hyperparameters, promoting responsible ML deployment in high-risk domains.

Contribution

It introduces the first system combining hyperparameter tuning, multiple fairness definitions, and Pareto frontier visualization for responsible ML model selection.

Findings

Enables exploration of models with diverse fairness metrics

Displays Pareto frontiers for informed decision-making

Supports responsible ML deployment in high-stakes areas

Abstract

Despite the potential benefits of machine learning (ML) in high-risk decision-making domains, the deployment of ML is not accessible to practitioners, and there is a risk of discrimination. To establish trust and acceptance of ML in such domains, democratizing ML tools and fairness consideration are crucial. In this paper, we introduce FairPilot, an interactive system designed to promote the responsible development of ML models by exploring a combination of various models, different hyperparameters, and a wide range of fairness definitions. We emphasize the challenge of selecting the ``best" ML model and demonstrate how FairPilot allows users to select a set of evaluation criteria and then displays the Pareto frontier of models and hyperparameters as an interactive map. FairPilot is the first system to combine these features, offering a unique opportunity for users to responsibly choose their model.