Search papers, labs, and topics across Lattice.
Moose introduces a novel approach for latent concept learning in OWL 2 EL ontologies by leveraging a Sentential Decision Diagram (SDD) as a differentiable weighted-model-counting layer. This method addresses the limitations of existing neuro-symbolic learning techniques by incorporating reasoning-shortcut awareness and enhancing expressivity through closure clauses. Experimental results demonstrate that Moose outperforms traditional propositional neuro-symbolic, fuzzy logic, and ontology embedding methods on benchmark tasks like MNIST-with-ontology and Pizza\"iolo.
Moose achieves unprecedented improvements in latent concept learning by integrating reasoning-shortcut awareness into OWL 2 EL ontologies, setting a new benchmark for neuro-symbolic methods.
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 $\mathcal{EL}^{++}$ 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 $\mathcal{EL}^{++}$ profile on declared exhaustive families to overcome the limited expressivity of $\mathcal{EL}^{++}$ 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 Pizza\"iolo. Moose improves over propositional-NeSy, fuzzy-logic, and ontology embedding baselines, and presents the first reasoning-shortcut analysis in an OWL EL setting.
