Score: 0

The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic

Published: May 12, 2025 | arXiv ID: 2505.08021v2

By: Bernardo Cuenca Grau, Eva Feng, Przemysław A. Wałęga

Potential Business Impact:

Lets computers understand complex connections better.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Graph Neural Networks (GNNs) address two key challenges in applying deep learning to graph-structured data: they handle varying size input graphs and ensure invariance under graph isomorphism. While GNNs have demonstrated broad applicability, understanding their expressive power remains an important question. In this paper, we propose GNN architectures that correspond precisely to prominent fragments of first-order logic (FO), including various modal logics as well as more expressive two-variable fragments. To establish these results, we apply methods from finite model theory of first-order and modal logics to the domain of graph representation learning. Our results provide a unifying framework for understanding the logical expressiveness of GNNs within FO.

Country of Origin
🇬🇧 United Kingdom

Page Count
21 pages

Category
Computer Science:
Artificial Intelligence