将一阶时序逻辑融入神经符号系统，实现可微分的动态知识推理。
First-Order Temporal Logic Tensor Networks
- 结合一阶时序逻辑语法与模糊语义，支持时间算子与量词。
- 在两个合成数据集上完成时序知识图谱补全，性能优于纯神经方法。
- 适合需要动态推理的场景，如时序关系建模与智能决策。
现有神经符号AI大多聚焦静态知识，对象属性不随时间变化。时序神经符号研究仍不充分，主要针对时间区间逻辑或命题线性时序逻辑。缺乏对带谓词的线性时序逻辑模型，无法处理属性和关系随时间演变的对象。本文提出一阶时序逻辑张量网络（FOT-LTN），扩展了逻辑张量网络（LTN），引入线性时间维度。FOT-LTN融合一阶线性时序逻辑的语法与LTN的模糊（实值）语义，构建支持时间算子与量词且完全可微的框架。首次评估在两个合成数据集上的时序知识图谱补全任务中，FOT-LTN性能优于专用（纯神经）方法。
原文摘要 · Abstract (English)
Most of the existing neuro-symbolic AI methods focus on the scenario of static knowledge where objects do not change according to a temporal dimension. Temporal neuro-symbolic works are still under explored and are mainly developed for time-interval logic or propositional linear temporal logic. There is a lack of models studying linear temporal logics with predicates that deal with objects whose properties and relations change through the time. We present First-Order Temporal Logic Tensor Networks (FOT-LTN) that is an extension of Logic Tensor Networks (LTN) that fills this gap by considering a linear-temporal dimension. In particular, FOT-LTN joins the syntax of First-Order Linear Temporal Logic with the fuzzy (and real-valued) semantics of LTN obtaining a framework that supports both temporal operators and quantifiers and is totally differentiable. A first evaluation regards a temporal knowledge graph completion task on two synthetic datasets showing better performance of FOT-LTN with respect to dedicated (purely neural) methods.
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。