ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. Machine Learning and Artificial Intelligence
Volume 8 - 2025 | doi: 10.3389/frai.2025.1549085
Elucidating Linear Programs by Neural Encodings
Provisionally accepted
- 1Department of Computer Science, Darmstadt University of Technology, Darmstadt, Hesse, Germany
- 2Hessian Center for Artificial Intelligence hessian.AI, Darmstadt, Hesse, Germany
- 3Centre for Cognitive Science, Darmstadt University of Technology, Darmstadt, Hesse, Germany
- 4German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Rheinland-Pfalz, Germany
- 5Eindhoven University of Technology, Eindhoven, Netherlands
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Linear Programs (LPs) are one of the major building blocks of AI and have championed recent strides in differentiable optimizers for learning systems. While efficient solvers exist for even high-dimensional LPs, explaining their solutions has not received much attention yet, as explainable artificial intelligence (XAI) has mostly focused on deep learning models. LPs are mostly considered white-box and thus assumed simple to explain, but we argue that they are not easy to understand in terms of relationships between inputs and outputs. To mitigate this rather non-explainability of LPs we show how to adapt attribution methods by encoding LPs in a neural fashion. The encoding functions consider aspects such as the feasibility of the decision space, the cost attached to each input, and the distance to special points of interest. Using a variety of LPs, including a very large-scale LP with 10k dimensions, we demonstrate the usefulness of explanation methods using our neural LP encodings, although the attribution methods Saliency and LIME are indistinguishable for low perturbation levels. In essence, we demonstrate that LPs can and should be explained, which can be achieved by representing an LP as a neural network.
Keywords: XAI, linear programming, attributions, Neural Encodings, machine learning
Received: 20 Dec 2024; Accepted: 12 May 2025.
Copyright: © 2025 Busch, Zečević, Kersting and Dhami. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Florian Peter Busch, Department of Computer Science, Darmstadt University of Technology, Darmstadt, 64289, Hesse, Germany
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.