FairCompass: Operationalising Fairness in Machine Learning
This work addresses the gap in operationalising fairness for real-world AI systems, though it appears incremental by integrating existing techniques into a human-centered approach.
The authors tackled the lack of practical implementation of fairness tools in machine learning by proposing FairCompass, a human-in-the-loop visual analytical system for fairness auditing, and demonstrated its potential for real-world deployability in an evaluation.
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.