MUPAX: Multidimensional Problem Agnostic eXplainable AI

TL;DR

MUPAX is a deterministic, model-agnostic XAI method with guaranteed convergence that provides principled feature importance attribution across diverse data modalities, improving model accuracy and explanation consistency.

Contribution

MUPAX introduces a novel measure theoretic, convergence-guaranteed XAI technique applicable to any data dimension and loss function, enhancing explainability and trustworthiness.

Findings

Effective across multiple data modalities including 1D, 2D, and 3D.

Preserves and enhances model accuracy during explanation.

Outperforms existing XAI methods in precision and consistency.

Abstract

Robust XAI techniques should ideally be simultaneously deterministic, model agnostic, and guaranteed to converge. We propose MULTIDIMENSIONAL PROBLEM AGNOSTIC EXPLAINABLE AI (MUPAX), a deterministic, model agnostic explainability technique, with guaranteed convergency. MUPAX measure theoretic formulation gives principled feature importance attribution through structured perturbation analysis that discovers inherent input patterns and eliminates spurious relationships. We evaluate MUPAX on an extensive range of data modalities and tasks: audio classification (1D), image classification (2D), volumetric medical image analysis (3D), and anatomical landmark detection, demonstrating dimension agnostic effectiveness. The rigorous convergence guarantees extend to any loss function and arbitrary dimensions, making MUPAX applicable to virtually any problem context for AI. By contrast with other XAI methods that typically decrease performance when masking, MUPAX not only preserves but actually enhances model accuracy by capturing only the most important patterns of the original data. Extensive benchmarking against the state of the XAI art demonstrates MUPAX ability to generate precise, consistent and understandable explanations, a crucial step towards explainable and trustworthy AI systems. The source code will be released upon publication.