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

TL;DR

This paper shows that 1-Lipschitz neural networks trained with an optimal transport loss produce highly concentrated, low-noise saliency maps that align well with human explanations, improving interpretability and robustness.

Contribution

It introduces a novel training approach for 1-Lipschitz neural networks that enhances explainability through optimal transport-based saliency maps, outperforming existing methods.

Findings

Saliency maps are highly concentrated and low-noise.

Maps align well with human explanations on ImageNet.

Networks are scalable and maintain robustness.

Abstract

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 of the image with low noise, significantly outperforming state-of-the-art explanation approaches across various models and metrics. We also prove that these maps align unprecedentedly well with human explanations on ImageNet.To explain the particularly beneficial properties of the Saliency Map for such models, we prove this gradient encodes both the direction of the transportation plan and the direction towards the nearest adversarial attack. Following the gradient down to the decision boundary is no longer considered an adversarial attack, but rather a counterfactual explanation that explicitly transports the input from one class to another. Thus, Learning with such a loss jointly optimizes the classification objective and the alignment of the gradient, i.e. the Saliency Map, to the transportation plan direction.These networks were previously known to be certifiably robust by design, and we demonstrate that they scale well for large problems and models, and are tailored for explainability using a fast and straightforward method.