Moose: Latent concept learning with reasoning-shortcut awareness in EL^{++}

arXiv:2608.12961v1 Announce Type: new Abstract: The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) learning methods accept propositional theories or Datalog, and reasoning-shortcut (RS) awareness has not been investigated in ontology settings. We present Moose, a method that compiles an EL^{++} TBox and finite ABox to a Sentential Decision Diagram (SDD). The SDD acts as a differentiable weighted-model-counting layer, and we add closure clauses outside the EL^{++} profile on declared exhaustive families to overcome the limited expressivity of EL^{++} under partial supervision. We show termination, soundness, completeness, and polynomial intermediate sizes, and validate the proofs in Lean. We then define the first formal partial-supervision latent-concept-learning task over an OWL EL ontology, i.e., learning per-individual classifiers for latent concepts from observed ABox literals, and evaluate Moose on MNIST-with-ontology and Pizzaiolo. Moose improves over propositional-NeSy, fuzzy-logic, and ontology embedding baselines, and presents the first reasoning-shortcut analysis in an OWL EL setting.

Related

• CyberCane: Neuro-Symbolic RAG for Privacy-Preserving Phishing Detection with Formal Ontology Reasoning
• NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning
• Enhanced and Efficient Reasoning in Large Learning Models

Source: arXiv cs.AI | 2026-08-14