Explaining Decisions in ML Models: a Parameterized Complexity Analysis (Part I)
It addresses the problem of understanding explanation complexities for researchers in explainable AI, but is incremental as it builds on existing theoretical frameworks without introducing new methods.
This paper conducted a theoretical analysis of the parameterized complexity of explanation problems in transparent machine learning models, addressing abductive and contrastive explanations across various models like Decision Trees and Boolean Circuits, and filled a gap in explainable AI by providing foundational insights into these complexities.
This paper presents a comprehensive theoretical investigation into the parameterized complexity of explanation problems in various machine learning (ML) models. Contrary to the prevalent black-box perception, our study focuses on models with transparent internal mechanisms. We address two principal types of explanation problems: abductive and contrastive, both in their local and global variants. Our analysis encompasses diverse ML models, including Decision Trees, Decision Sets, Decision Lists, Boolean Circuits, and ensembles thereof, each offering unique explanatory challenges. This research fills a significant gap in explainable AI (XAI) by providing a foundational understanding of the complexities of generating explanations for these models. This work provides insights vital for further research in the domain of XAI, contributing to the broader discourse on the necessity of transparency and accountability in AI systems.