Explaining Decisions in ML Models: a Parameterized Complexity Analysis
It addresses the need for transparency and accountability in AI systems by theoretically analyzing explanation complexities, but it is incremental as it builds on existing XAI concepts without introducing new methods.
This paper tackles the problem of understanding the computational complexity of generating explanations for various machine learning models, such as Decision Trees and Random Forests, by analyzing abductive and contrastive explanation problems, and it provides a foundational theoretical framework without specific numerical results.
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, Ordered Binary Decision Diagrams, Random Forests, and 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.