QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations

TL;DR

This paper introduces QUCE, a method that reduces path-based uncertainty in DNN explanations and generates more reliable counterfactual explanations by quantifying and minimizing uncertainty during out-of-distribution traversal.

Contribution

The paper proposes QUCE, a novel approach that minimizes path uncertainty in explainable DNN models and improves the quality of counterfactual explanations.

Findings

QUCE effectively reduces out-of-distribution path traversal uncertainty.

QUCE provides more reliable and certain counterfactual explanations.

Performance comparisons show QUCE outperforms existing methods in explanation quality.

Abstract

Deep Neural Networks (DNNs) stand out as one of the most prominent approaches within the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent increases in computational capacity, allowing these approaches to scale to significant complexities for addressing predictive challenges in big data. However, as the complexity of DNN models rises, interpretability diminishes. In response to this challenge, explainable models such as Adversarial Gradient Integration (AGI) leverage path-based gradients provided by DNNs to elucidate their decisions. Yet the performance of path-based explainers can be compromised when gradients exhibit irregularities during out-of-distribution path traversal. In this context, we introduce Quantified Uncertainty Counterfactual Explanations (QUCE), a method designed to mitigate out-of-distribution traversal by minimizing path uncertainty. QUCE not only quantifies uncertainty when presenting explanations but also generates more certain counterfactual examples. We showcase the performance of the QUCE method by comparing it with competing methods for both path-based explanations and generative counterfactual examples.