Fair Feature Importance Scores via Feature Occlusion and Permutation
This work addresses the need for interpretable and equitable models in fairness contexts, providing new tools for responsible machine learning development, though it is incremental as it builds on existing feature importance metrics for accuracy.
The paper tackles the problem of measuring how individual features influence fairness in machine learning models by proposing two model-agnostic methods: one based on permuting feature values and another on occluding features with computational simplification via minipatch learning. The results show that these methods are simple, scalable, and effective for multiple predictive tasks.
As machine learning models increasingly impact society, their opaque nature poses challenges to trust and accountability, particularly in fairness contexts. Understanding how individual features influence model outcomes is crucial for building interpretable and equitable models. While feature importance metrics for accuracy are well-established, methods for assessing feature contributions to fairness remain underexplored. We propose two model-agnostic approaches to measure fair feature importance. First, we propose to compare model fairness before and after permuting feature values. This simple intervention-based approach decouples a feature and model predictions to measure its contribution to training. Second, we evaluate the fairness of models trained with and without a given feature. This occlusion-based score enjoys dramatic computational simplification via minipatch learning. Our empirical results reflect the simplicity and effectiveness of our proposed metrics for multiple predictive tasks. Both methods offer simple, scalable, and interpretable solutions to quantify the influence of features on fairness, providing new tools for responsible machine learning development.