XpertAI: uncovering regression model strategies for sub-manifolds
It addresses the problem of providing precise explanations for regression models, which is incremental as it builds on existing XAI techniques.
The paper tackles the lack of Explainable AI (XAI) methods for regression models by introducing XpertAI, a framework that disentangles prediction strategies into range-specific sub-strategies to address precise user queries, with results showing benefits in qualitative and quantitative evaluations.
In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g.\ distinguishing between `Why is the output above 0?' and `Why is the output above 50?'). They should furthermore reflect the model's behavior on the relevant data sub-manifold. In this paper, we introduce XpertAI, a framework that disentangles the prediction strategy into multiple range-specific sub-strategies and allows the formulation of precise queries about the model (the `explanandum') as a linear combination of those sub-strategies. XpertAI is formulated generally to work alongside popular XAI attribution techniques, based on occlusion, gradient integration, or reverse propagation. Qualitative and quantitative results, demonstrate the benefits of our approach.