Saved in:
Bibliographic Details
Main Authors: Sälzer, Marco, Bergsträßer, Pascal, Lin, Anthony W.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.10393
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914553593331712
author Sälzer, Marco
Bergsträßer, Pascal
Lin, Anthony W.
author_facet Sälzer, Marco
Bergsträßer, Pascal
Lin, Anthony W.
contents The counting power of Message Passing Neural Networks (MPNN) has been the subject of many recent papers, showing that they can express logic that involves counting up to a threshold or more generally satisfy a linear arithmetic constraint. In this paper, we study the counting capabilities of MPNN beyond linear arithmetic, primarily utilising local and global mean aggregations. In particular, our goal is to tease out conditions required to express extensions of graded modal logic with polynomial counting constraints. We show that global polynomial counting constraints in node-labelled graphs can be checked using mean MPNN under mild assumptions. Checking local constraints is also possible, if we consider formulas with no nested modalities and additionally either (i) permit sum/max aggregations, or (ii) only restrict to regular graphs. We also show how formulas with nested modalities can be captured by mean MPNN over graphs with tree-like structures and similar assumptions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10393
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Polynomial Counting Capabilities of Message Passing Neural Networks
Sälzer, Marco
Bergsträßer, Pascal
Lin, Anthony W.
Machine Learning
Logic in Computer Science
The counting power of Message Passing Neural Networks (MPNN) has been the subject of many recent papers, showing that they can express logic that involves counting up to a threshold or more generally satisfy a linear arithmetic constraint. In this paper, we study the counting capabilities of MPNN beyond linear arithmetic, primarily utilising local and global mean aggregations. In particular, our goal is to tease out conditions required to express extensions of graded modal logic with polynomial counting constraints. We show that global polynomial counting constraints in node-labelled graphs can be checked using mean MPNN under mild assumptions. Checking local constraints is also possible, if we consider formulas with no nested modalities and additionally either (i) permit sum/max aggregations, or (ii) only restrict to regular graphs. We also show how formulas with nested modalities can be captured by mean MPNN over graphs with tree-like structures and similar assumptions.
title The Polynomial Counting Capabilities of Message Passing Neural Networks
topic Machine Learning
Logic in Computer Science
url https://arxiv.org/abs/2605.10393