On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective

Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations.However, Saliency Maps generated by traditional neural networks are often noisy and provide limited insights. In this paper, we demonstrate that, on the contrary, the Saliency Maps of 1-Lipschitz neural networks, learned with the dual loss of an optimal transportation problem, exhibit desirable XAI properties:They are highly concentrated on the essential parts …

adversarial ai techniques algorithms applications counterfactual cs.ai cs.cr cs.cv cs.lg explainable ai generated insights maps model robustness networks neural networks paper perspective pivotal robustness role stat.ml transport