FairAutoML: Embracing Unfairness Mitigation in AutoML
This work addresses fairness in AutoML for users deploying automated machine learning systems, but it is incremental as it builds on existing AutoML systems and fairness techniques.
The authors tackled the problem of integrating fairness considerations into Automated Machine Learning (AutoML) by proposing the FairAutoML framework, which dynamically allocates resources to balance prediction accuracy and unfairness mitigation, resulting in improved 'fair accuracy' and resource efficiency as shown in empirical evaluations.
In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair. We first investigate the necessity and impact of unfairness mitigation in the AutoML context. We establish the FairAutoML framework. The framework provides a novel design based on pragmatic abstractions, which makes it convenient to incorporate existing fairness definitions, unfairness mitigation techniques, and hyperparameter search methods into the model search and evaluation process. Following this framework, we develop a fair AutoML system based on an existing AutoML system. The augmented system includes a resource allocation strategy to dynamically decide when and on which models to conduct unfairness mitigation according to the prediction accuracy, fairness, and resource consumption on the fly. Extensive empirical evaluation shows that our system can achieve a good `fair accuracy' and high resource efficiency.