On the expressive power of message-passing neural networks as global feature map transformers

DOI10.1007/978-3-031-11321-5_2MaRDI QIDQ2103899zbMATH OpenOpenAlexFDO

Authors Floris Geerts, Jasper Steegmans, Jan Van den Bussche

Publication date 9 December 2022

Full work available at URL https://arxiv.org/abs/2203.09555

zbMATH Keywords

closure under concatenationquery languages for numerical datasemiring provenance semantics for modal logic

Mathematics Subject Classification ID

Database theory (68P15) Logic in artificial intelligence (68T27) Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35) Computing methodologies for information systems (hypertext navigation, interfaces, decision support, etc.) (68U35)

Cites work

• Deep learning
• Graph Representation Learning
• scientific article; zbMATH DE number 3539473 (Why is no real title available?)
• scientific article; zbMATH DE number 783783 (Why is no real title available?)
• scientific article; zbMATH DE number 839556 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• On the expressive power of linear algebra on graphs
• On the expressive power of query languages for matrices
• Semiring Provenance for Guarded Logics
• Understanding machine learning. From theory to algorithms
• Weak models of distributed computing, with connections to modal logic

Cited in

(1)

• The descriptive complexity of graph neural networks

Describes a project that uses

Uses Software

• MATLANG

This page was built for publication: On the expressive power of message-passing neural networks as global feature map transformers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2103899)