Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems
arXiv:2501.01441 · doi:10.1145/3706598.3713497
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.
Pre-print version, please cite the main article instead of the pre-print version
References in corpus (8)
- A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks
- Incorporating Domain Knowledge into Deep Neural Networks
- Representation Bias in Data: A Survey on Identification and Resolution Techniques
- Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations
- EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations
- Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions
- An Explanatory Model Steering System for Collaboration between Domain Experts and AI
- Representation Debiasing of Generated Data Involving Domain Experts