AI Chat AI Image Generator AI Video Text to Speech

A Modal Logic for Explaining some Graph Neural Networks

07/11/2023

∙

by Pierre Nunn, et al.

∙

∙

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.

Pierre Nunn
1 publication
François Schwarzentruber
11 publications

page 1

page 2

page 3

page 4

research

∙ 06/28/2019

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

This paper presents a new Graph Neural Network (GNN) type using feature-...

0 Marc Brockschmidt, et al. ∙

research

∙ 04/27/2019

Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers

In this paper, we investigate the feasibility of learning GNN (Graph Neu...

0 Zhanfu Yang, et al. ∙

research

∙ 03/22/2023

Logical Expressiveness of Graph Neural Network for Knowledge Graph Reasoning

Graph Neural Networks (GNNs) have been recently introduced to learn from...

0 Haiquan Qiu, et al. ∙

research

∙ 03/17/2023

Distill n' Explain: explaining graph neural networks using simple surrogates

Explaining node predictions in graph neural networks (GNNs) often boils ...

1 Tamara Pereira, et al. ∙

research

∙ 03/02/2023

Technical report: Graph Neural Networks go Grammatical

This paper proposes a new GNN design strategy. This strategy relies on C...

0 Jason Piquenot, et al. ∙

research

∙ 02/26/2020

Explaining Non-Bisimilarity in a Coalgebraic Approach: Games and Distinguishing Formulas

Behavioural equivalences can be characterized via bisimulation, modal lo...

0 Barbara König, et al. ∙

research

∙ 03/06/2023

Wind Turbine Gearbox Fault Detection Based on Sparse Filtering and Graph Neural Networks

The wind energy industry has been experiencing tremendous growth and con...

0 Jinsong Wang, et al. ∙