English
Related papers

Related papers: Logical Characterizations of Recurrent Graph Neura…

200 papers

We study the expressive power of graph neural networks (GNNs) with mean as the aggregation function, with the following results. In the non-uniform setting, such GNNs have exactly the same expressive power as ratio modal logic, which has…

Artificial Intelligence · Computer Science 2025-12-22 Moritz Schönherr , Carsten Lutz

We give an alternative proof for the existing result that recurrent graph neural networks working with reals have the same expressive power in restriction to monadic second-order logic MSO as the graded modal substitution calculus. The…

Logic in Computer Science · Computer Science 2025-05-16 Veeti Ahvonen , Damian Heiman , Antti Kuusisto

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…

Machine Learning · Computer Science 2025-10-29 Marco Sälzer , Przemysław Andrzej Wałęga , Martin Lange

We characterise the computational power of recurrent graph neural networks (GNNs) in terms of arithmetic circuits over the real numbers. Our networks are not restricted to aggregate-combine GNNs or other particular types. Generalising…

Computational Complexity · Computer Science 2026-05-05 Timon Barlag , Vivian Holzapfel , Laura Strieker , Jonni Virtema , Heribert Vollmer

Graph neural networks (GNNs) are a widely used class of machine learning models for graph-structured data, based on local aggregation over neighbors. GNNs have close connections to logic. In particular, their expressive power is linked to…

Logic in Computer Science · Computer Science 2026-01-30 Arie Soeteman , Michael Benedikt , Martin Grohe , Balder ten Cate

The expressivity of Graph Neural Networks (GNNs) can be described via appropriate fragments of the first order logic. Any query of the two variable fragment of graded modal logic (GC2) interpreted over labeled graphs can be expressed using…

Machine Learning · Computer Science 2024-08-14 Sammy Khalife

We precisely characterize the expressivity of computable Recurrent Graph Neural Networks (recurrent GNNs). We prove that recurrent GNNs with finite-precision parameters, sum aggregation, and ReLU activation, can compute any graph algorithm…

Machine Learning · Computer Science 2026-03-17 Eran Rosenbluth , Martin Grohe

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…

Artificial Intelligence · Computer Science 2026-02-20 Bernardo Cuenca Grau , Eva Feng , Przemysław Andrzej Wałęga

We study the expressive power of message-passing aggregate-combine-readout graph neural networks (ACR-GNNs). Particularly, we focus on the first-order (FO) properties expressible by this formalism. While a tight logical characterisation…

Machine Learning · Computer Science 2026-04-28 Maurice Funk , Daumantas Kojelis

In recent years, there has been growing interest in understanding the expressive power of graph neural networks (GNNs) by relating them to logical languages. This research has been been initialised by an influential result of Barcel\'o et…

Artificial Intelligence · Computer Science 2025-08-11 Stan P Hauke , Przemysław Andrzej Wałęga

Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms…

Machine Learning · Computer Science 2022-01-11 Martin Grohe

Graph neural networks (GNNs) are effective models for representation learning on relational data. However, standard GNNs are limited in their expressive power, as they cannot distinguish graphs beyond the capability of the Weisfeiler-Leman…

Machine Learning · Computer Science 2021-06-07 Ralph Abboud , İsmail İlkan Ceylan , Martin Grohe , Thomas Lukasiewicz

Recurrent Graph Neural Networks (RGNNs) extend standard GNNs by iterating message-passing until some stopping condition is met. Various RGNN models have been proposed in the literature. In this paper, we study three such models: converging…

Machine Learning · Computer Science 2026-04-29 Jeroen Bollen , Stijn Vansummeren

Graph neural networks (GNNs) have limited expressive power, failing to represent many graph classes correctly. While more expressive graph representation learning (GRL) alternatives can distinguish some of these classes, they are…

Machine Learning · Computer Science 2021-12-08 Leonardo Cotta , Christopher Morris , Bruno Ribeiro

We analyze the performance of graph neural network (GNN) architectures from the perspective of random graph theory. Our approach promises to complement existing lenses on GNN analysis, such as combinatorial expressive power and worst-case…

Machine Learning · Computer Science 2023-10-12 Drake Brown , Trevor Garrity , Kaden Parker , Jason Oliphant , Stone Carson , Cole Hanson , Zachary Boyd

We propose a modal logic in which counting modalities appear in linear inequalities. We show that each formula can be transformed into an equivalent graph neural network (GNN). We also show that a broad class of GNNs can be transformed…

Artificial Intelligence · Computer Science 2025-03-28 Pierre Nunn , Marco Sälzer , François Schwarzentruber , Nicolas Troquard

The study of Graph Neural Networks has received considerable interest in the past few years. By extending deep learning to graph-structured data, GNNs can solve a diverse set of tasks in fields including social science, chemistry, and…

Machine Learning · Computer Science 2024-03-12 Ashwin Nalwade , Kelly Marshall , Axel Eladi , Umang Sharma

We characterize the computational power of neural networks that follow the graph neural network (GNN) architecture, not restricted to aggregate-combine GNNs or other particular types. We establish an exact correspondence between the…

Machine Learning · Computer Science 2024-11-22 Timon Barlag , Vivian Holzapfel , Laura Strieker , Jonni Virtema , Heribert Vollmer

Graph neural networks (GNN) are deep learning architectures for graphs. Essentially, a GNN is a distributed message passing algorithm, which is controlled by parameters learned from data. It operates on the vertices of a graph: in each…

Logic in Computer Science · Computer Science 2024-05-21 Martin Grohe , Eran Rosenbluth

Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the expressive power of GNNs mainly focuses on simple…

Artificial Intelligence · Computer Science 2026-02-02 Han Yu , Xiaojuan Zhao , Aiping Li , Kai Chen , Ziniu Liu , Zhichao Peng
‹ Prev 1 2 3 10 Next ›