Explaining Decisions in ML Models: a Parameterized Complexity Analysis (Part I)

TL;DR

This paper conducts a detailed parameterized complexity analysis of explanation problems in transparent ML models, covering abductive and contrastive explanations across various model types to advance understanding in explainable AI.

Contribution

It provides a comprehensive theoretical framework analyzing the computational complexity of explanation tasks in multiple transparent ML models, filling a key gap in XAI research.

Findings

Complexity results vary across models and explanation types.

Certain explanation problems are computationally hard, others are tractable.

The analysis offers foundational insights for developing efficient explanation methods.

Abstract

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.