MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation. (arXiv:2205.15540v1 [cs.AI])

Counterfactual explanation is an important Explainable AI technique to
explain machine learning predictions. Despite being studied actively, existing
optimization-based methods often assume that the underlying machine-learning
model is differentiable and treat categorical attributes as continuous ones,
which restricts their real-world applications when categorical attributes have
many different values or the model is non-differentiable. To make
counterfactual explanation suitable for real-world applications, we propose a
novel framework of Model-Agnostic Counterfactual Explanation (MACE), which
adopts a newly designed pipeline that can efficiently …

ai arxiv framework model-agnostic