Uncertainty Quantification as a Principled Foundation for Explainable Artificial Intelligence: A Case Study of Counterfactual Explanations

TL;DR

This paper proposes a novel uncertainty-based framework for counterfactual explanations in AI, demonstrating its effectiveness and advocating for foundational AI concepts in transparency research.

Contribution

It introduces a principled uncertainty quantification approach to counterfactual explainability, unifying core properties and showing competitive performance with simple design.

Findings

Uncertainty-based explainer achieves state-of-the-art performance.

Framework is simple yet highly effective.

Integrating AI fundamentals enhances transparency and robustness.

Abstract

In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncertainty quantification in the context of counterfactual explainability, demonstrating that its broader adoption could address key challenges in the field. To this end, we show how uncertainty can provide a principled unifying framework for counterfactual explainability by expressing the core counterfactual properties in terms of uncertainty, allowing us to build two variants of an explainer upon them -- one based solely on uncertainty estimates and another pairing them with distance measured in the feature space. Our comprehensive experiments illustrate highly competitive performance of our framework when compared to many state-of-the-art methods despite its radically simple design. More broadly, the paper demonstrates that integrating artificial intelligence fundamentals into transparency research promises to yield more reliable, robust and understandable predictive models. We posit that making artificial intelligence explainability truly uncertainty-aware is the first step towards this goal.