License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.AIB.2022.5
URN: urn:nbn:de:0030-drops-160035
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2022/16003/
Go to the corresponding OASIcs Volume Portal

Jaeger, Manfred

Learning and Reasoning with Graph Data: Neural and Statistical-Relational Approaches (Invited Paper)

pdf-format:
OASIcs-AIB-2022-5.pdf (1 MB)

Abstract

Graph neural networks (GNNs) have emerged in recent years as a very powerful and popular modeling tool for graph and network data. Though much of the work on GNNs has focused on graphs with a single edge relation, they have also been adapted to multi-relational graphs, including knowledge graphs. In such multi-relational domains, the objectives and possible applications of GNNs become quite similar to what for many years has been investigated and developed in the field of statistical relational learning (SRL). This article first gives a brief overview of the main features of GNN and SRL approaches to learning and reasoning with graph data. It analyzes then in more detail their commonalities and differences with respect to semantics, representation, parameterization, interpretability, and flexibility. A particular focus will be on relational Bayesian networks (RBNs) as the SRL framework that is most closely related to GNNs. We show how common GNN architectures can be directly encoded as RBNs, thus enabling the direct integration of "low level" neural model components with the "high level" symbolic representation and flexible inference capabilities of SRL.

BibTeX - Entry

@InProceedings{jaeger:OASIcs.AIB.2022.5,
  author =	{Jaeger, Manfred},
  title =	{{Learning and Reasoning with Graph Data: Neural and Statistical-Relational Approaches}},
  booktitle =	{International Research School in Artificial Intelligence in Bergen (AIB 2022)},
  pages =	{5:1--5:42},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-228-0},
  ISSN =	{2190-6807},
  year =	{2022},
  volume =	{99},
  editor =	{Bourgaux, Camille and Ozaki, Ana and Pe\~{n}aloza, Rafael},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2022/16003},
  URN =		{urn:nbn:de:0030-drops-160035},
  doi =		{10.4230/OASIcs.AIB.2022.5},
  annote =	{Keywords: Graph neural networks, Statistical relational learning}
}

Keywords: Graph neural networks, Statistical relational learning
Collection: International Research School in Artificial Intelligence in Bergen (AIB 2022)
Issue Date: 2022
Date of publication: 25.05.2022

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI