A Modal Logic for Explaining some Graph Neural Networks

Pierre Nunn, François Schwarzentruber
7/11/2023
cs.AIcs.LO

No confident code implementation found for this paper.

Abstract

In this paper, 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 each GNN can be transformed into a formula. We show that the satisfiability problem is decidable. We also discuss some variants that are in PSPACE.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Logic for Reasoning About Aggregate-Combine Graph Neural Networks

92% match2024

Lecture Notes on Verifying Graph Neural Networks

90% match2025

Structural Preservation and the Logical Expressiveness of Graph Neural Networks

81% match2026

The logic of rational graph neural networks

80% match2023

Logical Characterizations of GNNs with Mean Aggregation

79% match2025

Logical Characterizations of Recurrent Graph Neural Networks with Reals and Floats

79% match2024

Cite this paper

@article{nunn2023modal,
  title  = {A Modal Logic for Explaining some Graph Neural Networks},
  author = {Pierre Nunn and François Schwarzentruber},
  year   = {2023},
  eprint = {2307.05150},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.05150v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.05150.svg)](https://codeofpaper.com/paper/2307.05150)

Discussion