CohEx: A Generalized Framework for Cohort Explanation
This work addresses the need for more nuanced model transparency in AI, offering a middle ground between global and local explanations for practitioners.
The paper tackles the gap in explainable AI by focusing on cohort-based explanations, which analyze model behavior on specific groups of instances, and introduces a generalized framework using supervised clustering to generate such explanations.
eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering.