Moose：在$\boldsymbol{\textit{EL}^{++}}$中具备推理捷径感知的潜在概念学习
Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
浏览论文内容
中文总结 AI 辅助
Moose是在$\boldsymbol{\textit{EL}^{++}}$中编译本体为SDD的方法，可实现部分监督下的潜在概念学习，在相关基准上优于多种基线，还完成了OWL EL设置下的首次推理捷径分析。
中文摘要 AI 辅助
OWL 2 EL概要被用于一些最大型的生产本体，包括基因本体（Gene Ontology）和SNOMED CT。现有神经符号（NeSy）学习方法接受命题理论或Datalog，且尚未在本体设置中研究过推理捷径（RS）感知。我们提出Moose，一种将$\boldsymbol{\textit{EL}^{++}}$术语盒（TBox）和有限断言盒（ABox）编译为句子决策图（SDD）的方法。SDD作为可微的加权模型计数层，我们在$\boldsymbol{\textit{EL}^{++}}$概要之外的已声明穷举族上添加闭包子句，以克服部分监督下$\boldsymbol{\textit{EL}^{++}}$表达能力有限的问题。我们证明了该方法的终止性、可靠性、完备性及多项式中间规模，并在Lean中验证了这些证明。随后，我们定义了首个针对OWL EL本体的形式化部分监督潜在概念学习任务，即从观测到的ABox文字学习针对潜在概念的个体分类器，并在MNIST-with-ontology和Pizzaïolo上评估Moose。Moose优于命题神经符号、模糊逻辑及本体嵌入基线方法，且在OWL EL设置中开展了首次推理捷径分析。
英文摘要
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.
发表机构
- King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
机构由 AI 辅助整理，请以论文原文为准。
