FairCompass: Operationalising Fairness in Machine Learning

TL;DR

FairCompass is a human-in-the-loop visual analytical system designed to operationalize fairness auditing in machine learning, addressing practical deployment challenges and promoting responsible AI through integrated subgroup discovery and decision tree techniques.

Contribution

The paper introduces FairCompass, a novel mixed visual analytical system that combines subgroup discovery and decision trees with an exploration-guided loop for fairness auditing in real-world ML applications.

Findings

Demonstrated effectiveness of FairCompass in real-world fairness auditing scenarios.

Showed potential for practical deployment of fairness tools in industry.

Facilitated human-centered fairness analysis in machine learning systems.

Abstract

As artificial intelligence (AI) increasingly becomes an integral part of our societal and individual activities, there is a growing imperative to develop responsible AI solutions. Despite a diverse assortment of machine learning fairness solutions is proposed in the literature, there is reportedly a lack of practical implementation of these tools in real-world applications. Industry experts have participated in thorough discussions on the challenges associated with operationalising fairness in the development of machine learning-empowered solutions, in which a shift toward human-centred approaches is promptly advocated to mitigate the limitations of existing techniques. In this work, we propose a human-in-the-loop approach for fairness auditing, presenting a mixed visual analytical system (hereafter referred to as 'FairCompass'), which integrates both subgroup discovery technique and the decision tree-based schema for end users. Moreover, we innovatively integrate an Exploration, Guidance and Informed Analysis loop, to facilitate the use of the Knowledge Generation Model for Visual Analytics in FairCompass. We evaluate the effectiveness of FairCompass for fairness auditing in a real-world scenario, and the findings demonstrate the system's potential for real-world deployability. We anticipate this work will address the current gaps in research for fairness and facilitate the operationalisation of fairness in machine learning systems.