
VeriTraCER introduces a novel approach to training models and generating counterfactual explanations that are robust to small model shifts. By optimizing over a multiplicity set of classifiers, VeriTraCER provides deterministic guarantees on the validity of counterfactual explanations.


coremsg

verified-training-for-counterfactual-explanation-robustness-under-data-shift


Verified Training for Counterfactual Explanation Robustness under Data Shift


title_rewrite


Providing theoretical guarantees on the robustness of counterfactuals to potential model changes.


robust-counterfactual-explanations-for-neural-networks-with-probabilistic-guarantees


Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
