Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach

Computer Science > Artificial Intelligence [Submitted on 8 Apr 2026] Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach Daniele Fossemò, Filippo Mignosi, Giuseppe Placidi, Luca Raggioli, Matteo Spezialetti, Fabio Aurelio D'Asaro In this paper, we propose using Learning from Answer Sets to approximate black-box models, such as Neural Networks (NN), in the specific case of learning user preferences. We specifically explore the use of ILASP (Inductive Learning of Answer Set Programs) to approximate preference learning systems through weak constraints. We have created a dataset on user preferences over a set of recipes, which is used to train the NNs that we aim to approximate with ILASP. Our experiments investigate ILASP both as a global and a local approximator of the NNs. These experiments address the challenge of approximating NNs working on increasingly high-dimensional feature spaces while achieving appropriate fidelity on the target model and limiting the increase in computational time. To handle this challenge, we propose a preprocessing step that exploits Principal Component Analysis to reduce the dataset's dimensionality while keeping our explanations transparent. Under consideration for publication in Theory and Practice of Logic Programming (TPLP). Comments: Under consideration for publication in Theory and Practice of Logic Programming (TPLP) Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2604.06838 [cs.AI]   (or arXiv:2604.06838v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.06838 Focus to learn more Submission history From: Daniele Fossemò [view email] [v1] Wed, 8 Apr 2026 09:00:12 UTC (1,606 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)