AI RESEARCH
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor
arXiv CS.AI
•
ArXi:2605.04193v1 Announce Type: new Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule search and is brittle under uncertainty, while differentiable ILP methods typically depend on predefined rule templates or inaccurate fuzzy operators that suffer from vanishing gradients or poor approximation of logical structure when reasoning over probabilistic predicate valuations.