用机器学习预测逻辑知识库的不一致程度，提升计算效率。
(Neural-Symbolic) Machine Learning for Inconsistency Measurement
- 设计回归与神经网络模型，学习预测不一致度量值
- 在多种场景下实现高精度预测，准确率显著提升
- 结合逻辑公理约束，增强模型可解释性与可靠性
我们提出基于机器学习的方法，用于确定命题逻辑知识库的不一致程度——这是一个数值。具体而言，我们构建了回归与神经网络模型，学习预测不一致度量 $\ ext{incmi}$ 与 $\ ext{incat}$ 对知识库所赋予的数值。主要动机是传统计算这些值在复杂度上较为困难。作为重要补充，我们利用度量本身所满足的特定公理（即性质），推导出符号规则，并以约束形式与学习模型结合。通过大量实验表明：a) 在许多情况下，预测不一致度值是可行的；b) 引入由合理性公理推导出的符号约束可有效提升预测质量。
原文摘要 · Abstract (English)
We present machine-learning-based approaches for determining the \emph{degree} of inconsistency -- which is a numerical value -- for propositional logic knowledge bases. Specifically, we present regression- and neural-based models that learn to predict the values that the inconsistency measures $\incmi$ and $\incat$ would assign to propositional logic knowledge bases. Our main motivation is that computing these values conventionally can be hard complexity-wise. As an important addition, we use specific postulates, that is, properties, of the underlying inconsistency measures to infer symbolic rules, which we combine with the learning-based models in the form of constraints. We perform various experiments and show that a) predicting the degree values is feasible in many situations, and b) including the symbolic constraints deduced from the rationality postulates increases the prediction quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。