Attributions Beyond Neural Networks: The Linear Program Case
This work addresses interpretability challenges in optimization for machine learning practitioners, but it is incremental as it adapts existing XAI methods to a new context.
The paper tackles the problem of understanding high-dimensional solutions in Linear Programs (LPs) by applying neural encodings and XAI attribution methods, showing that Saliency and LIME produce similar results and proposing Directedness as a discriminative criterion.
Linear Programs (LPs) have been one of the building blocks in machine learning and have championed recent strides in differentiable optimizers for learning systems. While there exist solvers for even high-dimensional LPs, understanding said high-dimensional solutions poses an orthogonal and unresolved problem. We introduce an approach where we consider neural encodings for LPs that justify the application of attribution methods from explainable artificial intelligence (XAI) designed for neural learning systems. The several encoding functions we propose take into account aspects such as feasibility of the decision space, the cost attached to each input, or the distance to special points of interest. We investigate the mathematical consequences of several XAI methods on said neural LP encodings. We empirically show that the attribution methods Saliency and LIME reveal indistinguishable results up to perturbation levels, and we propose the property of Directedness as the main discriminative criterion between Saliency and LIME on one hand, and a perturbation-based Feature Permutation approach on the other hand. Directedness indicates whether an attribution method gives feature attributions with respect to an increase of that feature. We further notice the baseline selection problem beyond the classical computer vision setting for Integrated Gradients.