ICGT 2023
Wed 19 - Thu 20 July 2023 Leicester, United Kingdom
co-located with STAF 2023
Thu 20 Jul 2023 09:30 - 10:00 at Willow - ICGT Session 5: Blue Skies & Journal-First Chair(s): Detlef Plump

Given graphs as input, Graph Neural Networks (GNNs) support the inference of nodes, edges, attributes, or graph properties. Graph Rewriting investigates the rule-based manipulation of graphs to model complex graph transformations.

We propose that, therefore, (i) graph rewriting subsumes GNNs and could serve as an operational semantic model to study and compare them, and (ii) the representation of GNNs as graph rewrite systems can help to design and analyse GNNs, their architectures and algorithms. Hence we propose Graph Rewriting Neural Networks (GReNN) as both novel semantic foundation and engineering discipline for GNNs.

We develop a case study of a Message Passing Neural Network and its realisation in graph rewriting and explore its incremental operation in the face of dynamic updates.

Sides: Graph Rewriting for Graph Neural Networks (grenn-lowres.pdf)6.35MiB

Thu 20 Jul

Displayed time zone: London change

09:00 - 10:30
ICGT Session 5: Blue Skies & Journal-FirstResearch Papers / Journal-First at Willow
Chair(s): Detlef Plump University of York

Remote Participants: Zoom Link, YouTube Livestream

A living monograph for graph transformation
Research Papers
Nicolas Behr CNRS, Université Paris Cité, IRIF, P: Russ Harmer CNRS
DOI File Attached
Graph Rewriting for Graph Neural NetworksNominated for Best Paper
Research Papers
Adam Machowczyk University of Leicester, P: Reiko Heckel University of Leicester
DOI File Attached
Compositionality of Rewriting Rules with Conditions
P: Nicolas Behr CNRS, Université Paris Cité, IRIF, Jean Krivine CNRS
DOI Media Attached