FairPilot: An Explorative System for Hyperparameter Tuning through the Lens of Fairness
This addresses the problem of democratizing ML tools and ensuring fairness for practitioners in high-risk decision-making domains, but it appears incremental as it combines existing features into a new system.
The paper tackles the challenge of making machine learning accessible and fair for practitioners in high-risk domains by introducing FairPilot, an interactive system that explores models, hyperparameters, and fairness definitions to help users select responsible models, though no concrete performance numbers are provided.
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.