The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sälzer, Marco, Wałęga, Przemysław Andrzej, Lange, Martin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908615898562560
author Sälzer, Marco
Wałęga, Przemysław Andrzej
Lange, Martin
author_facet Sälzer, Marco
Wałęga, Przemysław Andrzej
Lange, Martin
contents In recent years, the expressive power of various neural architectures -- including graph neural networks (GNNs), transformers, and recurrent neural networks -- has been characterised using tools from logic and formal language theory. As the capabilities of basic architectures are becoming well understood, increasing attention is turning to models that combine multiple architectural paradigms. Among them particularly important, and challenging to analyse, are temporal extensions of GNNs, which integrate both spatial (graph-structure) and temporal (evolution over time) dimensions. In this paper, we initiate the study of logical characterisation of temporal GNNs by connecting them to two-dimensional product logics. We show that the expressive power of temporal GNNs depends on how graph and temporal components are combined. In particular, temporal GNNs that apply static GNNs recursively over time can capture all properties definable in the product logic of (past) propositional temporal logic PTL and the modal logic K. In contrast, architectures such as graph-and-time TGNNs and global TGNNs can only express restricted fragments of this logic, where the interaction between temporal and spatial operators is syntactically constrained. These provide us with the first results on the logical expressiveness of temporal GNNs.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11930
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
Sälzer, Marco
Wałęga, Przemysław Andrzej
Lange, Martin
Machine Learning
Artificial Intelligence
Logic in Computer Science
In recent years, the expressive power of various neural architectures -- including graph neural networks (GNNs), transformers, and recurrent neural networks -- has been characterised using tools from logic and formal language theory. As the capabilities of basic architectures are becoming well understood, increasing attention is turning to models that combine multiple architectural paradigms. Among them particularly important, and challenging to analyse, are temporal extensions of GNNs, which integrate both spatial (graph-structure) and temporal (evolution over time) dimensions. In this paper, we initiate the study of logical characterisation of temporal GNNs by connecting them to two-dimensional product logics. We show that the expressive power of temporal GNNs depends on how graph and temporal components are combined. In particular, temporal GNNs that apply static GNNs recursively over time can capture all properties definable in the product logic of (past) propositional temporal logic PTL and the modal logic K. In contrast, architectures such as graph-and-time TGNNs and global TGNNs can only express restricted fragments of this logic, where the interaction between temporal and spatial operators is syntactically constrained. These provide us with the first results on the logical expressiveness of temporal GNNs.
title The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
topic Machine Learning
Artificial Intelligence
Logic in Computer Science
url https://arxiv.org/abs/2505.11930