发表机构
Simula Research Laboratory; Microsoft; LISN, CNRS, Paris-Saclay University（西穆拉研究实验室; 微软; 法国国家科学研究中心巴黎-萨克雷大学LISN实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种神经符号框架，利用神经Oracle Transformer模拟用户响应并与FastCA引擎交互，从示例中自动学习约束网络，减少人工参与，实现数据驱动模式识别与符号推理的有效结合。
AI 中文摘要
在约束获取（CA）文献中，将用户定义的概念学习为约束网络已被广泛研究。然而，现有方法通常依赖于与人类神谕的密集交互，使得学习过程在时间和查询数量方面成本高昂。在本文中，我们提出了一种用于自动约束获取的神经符号框架，通过引入神经Oracle Transformer模型来显著减少用户参与，这些模型学习模拟用户响应并泛化概念知识。在先前可用的示例上训练后，学习到的神谕与专用约束获取引擎FastCA交互，该引擎系统地将神谕的响应精炼为健全、一致且可解释的约束网络。这种神经符号交互使得无需先验领域知识即可从数据中恢复结构化符号模型。我们的结果表明，这种神经符号交互有效地将数据驱动的模式识别与符号推理对齐，为在组合领域中自动化模型构建提供了一种稳健的方法。
英文摘要
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 enables the recovery of structured symbolic models from data without prior domain knowledge. Our results demonstrate that this neuro-symbolic interplay effectively aligns data-driven pattern recognition with symbolic reasoning, offering a robust approach to automating model construction in combinatorial domains.
