Fair Bayesian Optimization

TL;DR

This paper presents a flexible Bayesian optimization framework that enforces fairness constraints across various ML models by tuning hyperparameters, achieving fairer and high-performing solutions without model-specific adjustments.

Contribution

It introduces a general, model-agnostic constrained Bayesian optimization method for optimizing ML performance with fairness constraints, applicable to diverse models and fairness definitions.

Findings

The approach achieves accurate and fair solutions by hyperparameter tuning.

It is competitive with specialized fairness techniques and outperforms data preprocessing methods.

Hyperparameters like regularization correlate with fairness and generalization.

Abstract

Given the increasing importance of machine learning (ML) in our lives, several algorithmic fairness techniques have been proposed to mitigate biases in the outcomes of the ML models. However, most of these techniques are specialized to cater to a single family of ML models and a specific definition of fairness, limiting their adaptibility in practice. We introduce a general constrained Bayesian optimization (BO) framework to optimize the performance of any ML model while enforcing one or multiple fairness constraints. BO is a model-agnostic optimization method that has been successfully applied to automatically tune the hyperparameters of ML models. We apply BO with fairness constraints to a range of popular models, including random forests, gradient boosting, and neural networks, showing that we can obtain accurate and fair solutions by acting solely on the hyperparameters. We also show empirically that our approach is competitive with specialized techniques that enforce model-specific fairness constraints, and outperforms preprocessing methods that learn fair representations of the input data. Moreover, our method can be used in synergy with such specialized fairness techniques to tune their hyperparameters. Finally, we study the relationship between fairness and the hyperparameters selected by BO. We observe a correlation between regularization and unbiased models, explaining why acting on the hyperparameters leads to ML models that generalize well and are fair.