Litcius/Paper detail

Fairness-aware configuration of machine learning libraries

Saeid Tizpaz-Niari, Ashish Kumar, Gang Tan, Ashutosh Trivedi

2022Proceedings of the 44th International Conference on Software Engineering44 citationsDOIOpen Access PDF

Abstract

This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount importance. The existing approaches focus on addressing fairness bugs by either modifying the input dataset or modifying the learning algorithms. On the other hand, the selection of hyperparameters, which provide finer controls of ML algorithms, may enable a less intrusive approach to influence the fairness. Can hyperparameters amplify or suppress discrimination present in the input dataset? How can we help programmers in detecting, understanding, and exploiting the role of hyperparameters to improve the fairness?

Topics & Concepts

HyperparameterComputer scienceMachine learningFocus (optics)Selection (genetic algorithm)Artificial intelligenceSoftwareSpace (punctuation)Data spaceProgramming languageOperating systemOpticsPhysicsAdversarial Robustness in Machine LearningEthics and Social Impacts of AIExplainable Artificial Intelligence (XAI)
Fairness-aware configuration of machine learning libraries | Litcius