Explainability for Machine Learning Models: From Data Adaptability to User Perception
It addresses the need for transparent and trustworthy AI systems for users and practitioners, though it appears incremental by enhancing existing methods and conducting comparative analyses.
This thesis tackled the problem of generating local explanations for deployed machine learning models by developing methods to ensure explanations are faithful to models and comprehensible to users, with results including comparative experiments on counterfactual methods and user studies measuring understanding and trust.
This thesis explores the generation of local explanations for already deployed machine learning models, aiming to identify optimal conditions for producing meaningful explanations considering both data and user requirements. The primary goal is to develop methods for generating explanations for any model while ensuring that these explanations remain faithful to the underlying model and comprehensible to the users. The thesis is divided into two parts. The first enhances a widely used rule-based explanation method. It then introduces a novel approach for evaluating the suitability of linear explanations to approximate a model. Additionally, it conducts a comparative experiment between two families of counterfactual explanation methods to analyze the advantages of one over the other. The second part focuses on user experiments to assess the impact of three explanation methods and two distinct representations. These experiments measure how users perceive their interaction with the model in terms of understanding and trust, depending on the explanations and representations. This research contributes to a better explanation generation, with potential implications for enhancing the transparency, trustworthiness, and usability of deployed AI systems.