2 papers
cs.LG2026
Provably Robust Bayesian Counterfactual Explanations under Model Changes
Jamie Duell, Xiuyi Fan
Counterfactual explanations (CEs) offer interpretable insights into machine learning predictions by answering ``what if?" questions. However, in real-world settings where models ar…
cs.LG2025
QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations
Jamie Duell, Monika Seisenberger, Hsuan Fu +1
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…