Explainable AI by BAPC -- Before and After correction Parameter Comparison

TL;DR

This paper introduces a local surrogate explanation method for AI models, specifically using a residual correction approach with linear regression as the base, analyzing the trade-offs between accuracy and fidelity.

Contribution

It presents a novel analytical framework for explaining AI predictions via residual correction, with criteria linking surrogate accuracy, fidelity, and data noise.

Findings

Criteria for optimal neighborhood size in explanations

Trade-offs between surrogate accuracy and fidelity

Analytical bounds under data noise assumptions

Abstract

A local surrogate for an AI-model correcting a simpler 'base' model is introduced representing an analytical method to yield explanations of AI-predictions. The approach is studied here in the context of the base model being linear regression. The AI-model approximates the residual error of the linear model and the explanations are formulated in terms of the change of the interpretable base model's parameters. Criteria are formulated for the precise relation between lost accuracy of the surrogate, the accuracy of the AI-model, and the surrogate fidelity. It is shown that, assuming a certain maximal amount of noise in the observed data, these criteria induce neighborhoods of the instances to be explained which have an ideal size in terms of maximal accuracy and fidelity.