First-Order Temporal Logic Tensor Networks
2026-06-29 • Artificial Intelligence
Artificial IntelligenceMachine LearningLogic in Computer Science
AI summaryⓘ
The authors present a new method called First-Order Temporal Logic Tensor Networks (FOT-LTN) that improves how AI handles knowledge changing over time. Unlike most existing methods, their approach can reason about objects and their relationships as they evolve through time using a logic that supports time and quantifiers. They tested FOT-LTN on tasks involving temporal knowledge graphs and found it performed better than some purely neural methods. This work addresses a gap in combining temporal reasoning with neuro-symbolic AI.
Neuro-symbolic AIFirst-Order Linear Temporal LogicTemporal reasoningLogic Tensor NetworksTemporal knowledge graph completionDifferentiable logicTemporal operatorsQuantifiers
Authors
Luca Boscarato, Ivan Donadello, Alessandro Artale, Marco Montali, Fabrizio Maria Maggi
Abstract
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.