Related papers: Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$

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

URL: http://arxiv.org/abs/2608.12961v1
Date: Thu, 13 Aug 2026 08:44:48 GMT
Title: Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
Abstract summary: We present Moose, a method that compiles an $mathcalEL$ TBox and finite ABox to a Sentential Decision Diagram (SDD)<n>We show first formal partial-supervision latent-concept over an OWL EL, i.e., learning per-individuals for latent concepts from observed ABox literals, and evaluate Moose on M-with-ontology and Pizzaolo.
Score: 40.07805055659496
License: http://creativecommons.org/licenses/by/4.0/
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 $\mathcal{EL}^{++}$ 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 Pizzaïolo. Moose improves over propositional-NeSy, fuzzy-logic, and ontology embedding baselines, and presents the first reasoning-shortcut analysis in an OWL EL setting.

Related papers

Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits [40.07805055659496]
Baobab compiles a $mathcalSROIQ$ ontology with a finite ABox into a Sentential Decision Diagram.<n>We show that a mixture indexed by the query's justifications can represent the calibrated posterior no independent perception can mitigate.
arXiv Detail & Related papers (2026-08-18T13:04:51Z)
Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval [59.859592671274704]
How many key-value associations can a $dtimes d$ linear memory store?<n>We show that the answer depends not only on the $d2$ degrees of freedom in the memory matrix, but also on the retrieval criterion.
arXiv Detail & Related papers (2026-05-06T17:53:20Z)
Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit [66.20349460098275]
We study the gradient descent learning of a general Gaussian Multi-index model $f(boldsymbolx)=g(boldsymbolUboldsymbolx)$ with hidden subspace $boldsymbolUin mathbbRrtimes d$.<n>We prove that under generic non-degenerate assumptions on the link function, a standard two-layer neural network trained via layer-wise gradient descent can agnostically learn the target with $o_d(1)$ test error.
arXiv Detail & Related papers (2025-11-19T04:46:47Z)
Lemmanaid: Neuro-Symbolic Lemma Conjecturing [4.821473821650318]
Lemmanaid is a practical neuro-symbolic lemma conjecturing tool.<n>It combines Large Language Models (LLMs) and symbolic methods.<n>We evaluate it on proof libraries for the Isabelle proof assistant.
arXiv Detail & Related papers (2025-04-07T11:30:36Z)
DELE: Deductive $\mathcal{EL}^{++}$ Embeddings for Knowledge Base Completion [42.53092500260737]
Ont embeddings map classes, roles, and individuals in into $mathcalEL++$, and within $bbRn$ similarity between entities can be computed or inferred.<n>We show that our embedding methods improve over the baseline embedding in the task of knowledge base completion.
arXiv Detail & Related papers (2024-11-03T14:00:04Z)
LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers [60.009969929857704]
Logical reasoning is an important task for artificial intelligence with potential impacts on science, mathematics, and society. In this work, we reformulating such tasks as modular neurosymbolic programming, which we call LINC. We observe significant performance gains on FOLIO and a balanced subset of ProofWriter for three different models in nearly all experimental conditions we evaluate.
arXiv Detail & Related papers (2023-10-23T17:58:40Z)
Lattice-preserving $\mathcal{ALC}$ ontology embeddings with saturation [50.05281461410368]
An order-preserving embedding method is proposed to generate embeddings of OWL representations. We show that our method outperforms state-the-art theory-of-the-art embedding methods in several knowledge base completion tasks.
arXiv Detail & Related papers (2023-05-11T22:27:51Z)
Dual Box Embeddings for the Description Logic EL++ [16.70961576041243]
Similar to Knowledge Graphs (KGs), Knowledge Graphs are often incomplete, and maintaining and constructing them has proved challenging. Similar to KGs, a promising approach is to learn embeddings in a latent vector space, while additionally ensuring they adhere to the semantics of the underlying DL. We propose a novel ontology embedding method named Box$2$EL for the DL EL++, which represents both concepts and roles as boxes.
arXiv Detail & Related papers (2023-01-26T14:13:37Z)
Description Logic EL++ Embeddings with Intersectional Closure [10.570100236658705]
We develop EL Embedding (ELBE) to learn Description Logic EL++ embeddings using axis-parallel boxes. We report extensive experimental results on three datasets and present a case study to demonstrate the effectiveness of the proposed method.
arXiv Detail & Related papers (2022-02-28T18:37:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.