[论文] Learning Symbolic Constraint Representations from Examples: A Neuro-Sy...

论文概要

研究领域: ML
作者: Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker
发布时间: 2026-09-15
arXiv: 2609.12267

中文摘要

将用户自定义概念学习为约束网络在约束获取（CA）文献中已被广泛研究。然而现有方法通常依赖与人类 oracle 的高强度交互，使学习过程在时间与查询次数上代价高昂。本文提出一个用于自动 CA 的神经符号框架，通过引入神经 Oracle Transformer 模型显著减少用户参与——这些模型学习模拟用户回答并泛化概念知识。训练于已有样本的学习型 oracle 与专用 CA 引擎 FastCA 交互，后者将 oracle 的回答系统性地精炼为可靠、一致且可解释的约束网络。这种神经符号交互使得在无需先验领域知识的情况下从数据中恢复结构化的符号模型成为可能。结果表明，这种神经符号协作有效地将数据驱动的模式识别与符号推理对齐，为组合优化领域的模型自动构建提供了一条稳健路径。

原文摘要

Learning user-defined concepts as constraint networks has been extensively studied in the constraint acquisition (CA) literature. However, existing approaches typically rely on intensive interactions with a human oracle, making the learning process costly in terms of time and number of queries. In this paper, we propose a neuro-symbolic framework for automatic CA that significantly reduces user involvement by introducing neural Oracle Transformer models which learn to emulate user responses and to generalize conceptual knowledge. Trained on previously available examples, the learned oracle interacts with a dedicated CA engine, FastCA, which systematically refines the oracle's responses into a sound, consistent, and interpretable constraint network. This neuro-symbolic interaction enabl...

自动采集于 2026-09-15

#论文 #arXiv #ML #小凯