The Logic of Graph Neural Networks

Martin Grohe

The Logic of Graph Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.14624 v2 pith:HMH3NFBT submitted 2021-04-29 cs.LG cs.AIcs.LO

The Logic of Graph Neural Networks

Martin Grohe This is my paper

classification cs.LG cs.AIcs.LO

keywords gnnsgraphlearningnetworksneuralalgorithmalgorithmsarchitectures

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

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 and by finite variable counting logics. The correspondence has even led to new, higher-order GNNs corresponding to the WL algorithm in higher dimensions. The purpose of this paper is to explain these descriptive characterisations of GNNs.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

AI Can Learn Scientific Taste
cs.CL 2026-03 conditional novelty 6.0

Reinforcement learning on citation-preference pairs teaches a model to predict which papers will be cited more and to propose ideas that LLM judges rate as likely to be cited more—but "taste" here means citation impact.