QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations
This addresses interpretability issues in complex DNNs for users needing reliable explanations, but it is incremental as it builds on existing path-based methods.
The paper tackles the problem of irregular gradients in path-based explainers for deep neural networks, which compromise interpretability, by introducing QUCE to minimize and quantify path uncertainty, resulting in more certain counterfactual examples and outperforming competing methods in evaluations.
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.