Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems

TL;DR

This paper proposes a set of design guidelines for involving domain experts in the data generation process to effectively reduce representation bias in AI systems, demonstrated through a healthcare application with positive results.

Contribution

It introduces generic guidelines for involving domain experts in data debiasing, addressing a gap in current AI bias mitigation methods.

Findings

Involving domain experts reduces representation bias effectively.

The approach maintains model accuracy while mitigating bias.

Guidelines improve the robustness of debiasing systems.

Abstract

Representation bias is one of the most common types of biases in artificial intelligence (AI) systems, causing AI models to perform poorly on underrepresented data segments. Although AI practitioners use various methods to reduce representation bias, their effectiveness is often constrained by insufficient domain knowledge in the debiasing process. To address this gap, this paper introduces a set of generic design guidelines for effectively involving domain experts in representation debiasing. We instantiated our proposed guidelines in a healthcare-focused application and evaluated them through a comprehensive mixed-methods user study with 35 healthcare experts. Our findings show that involving domain experts can reduce representation bias without compromising model accuracy. Based on our findings, we also offer recommendations for developers to build robust debiasing systems guided by our generic design guidelines, ensuring more effective inclusion of domain experts in the debiasing process.