Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Space

TL;DR

This paper introduces an interactive framework that uses metric learning and clustering to help stakeholders understand and select models based on fairness and performance trade-offs in algorithmic decision-making.

Contribution

It presents a novel approach combining weakly supervised metric learning and clustering to structure model feature importance for better interpretability and decision support.

Findings

Effective clustering of models based on fairness-performance trade-offs.

Enhanced interpretability of model differences through feature importance space.

Facilitated stakeholder decision-making in model selection.

Abstract

In the context of algorithmic decision-making, fair machine learning methods often yield multiple models that balance predictive fairness and performance in varying degrees. This diversity introduces a challenge for stakeholders who must select a model that aligns with their specific requirements and values. To address this, we propose an interactive framework that assists in navigating and interpreting the trade-offs across a portfolio of models. Our approach leverages weakly supervised metric learning to learn a Mahalanobis distance that reflects similarity in fairness and performance outcomes, effectively structuring the feature importance space of the models according to stakeholder-relevant criteria. We then apply clustering technique (k-means) to group models based on their transformed representations of feature importances, allowing users to explore clusters of models with similar predictive behaviors and fairness characteristics. This facilitates informed decision-making by helping users understand how models differ not only in their fairness-performance balance but also in the features that drive their predictions.