Potential Energy to Improve Link Prediction With Relational Graph Neural Networks

Simone Colombo*, Dimitrios Alivanistos, Michael Cochez

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Potential Energy (PE) between 2 bodies with mass, refers to the relative gravitational pull between them. Analogously, in the context of a graph, nodes can thought of as objects where a) the product of the degrees of nodes acts as a proxy for mass, b) the clustering coefficients of common neighbours as a proxy for gravitational acceleration, and c) the inverse of the shortest distance between nodes as a proxy for distance in space, which allows for PE calculation as introduced in prior work. In this work, we are investigating the effects of incorporating PE in Link Prediction (LP) with Relational Graph Convolutional Networks (R-GCN). Specifically, we explore the benefits of including PE calculation as an informative prior to the LP task and in a follow-up experiment as a learnable feature to predict. We performed several experiments and show that considering PE in the LP process has certain advantages and find that the information PE provides was not captured by the embeddings produced by the R-GCN.

Original languageEnglish
Title of host publicationAAAI-MAKE 2022 Machine Learning and Knowledge Engineering for Hybrid Intelligence 2022
Subtitle of host publicationProceedings of the AAAI 2022 Spring Symposium on Machine Learning and Knowledge Engineering for Hybrid Intelligence (AAAI-MAKE 2022) Stanford University, Palo Alto, California, USA, March 21-23, 2022
EditorsAndreas Martin, Knut Hinkelmann, Hans-Georg Fill, Aurona Gerber, Doug Lenat, Reinhard Stolle, Frank van Harmelen
PublisherCEUR-WS.org
Pages1-9
Number of pages9
Publication statusPublished - 21 Mar 2022
EventAAAI 2022 Spring Symposium on Machine Learning and Knowledge Engineering for Hybrid Intelligence, AAAI-MAKE 2022 - Palo Alto, United States
Duration: 21 Mar 202223 Mar 2022

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR Workshop Proceedings
Volume3121
ISSN (Print)1613-0073

Conference

ConferenceAAAI 2022 Spring Symposium on Machine Learning and Knowledge Engineering for Hybrid Intelligence, AAAI-MAKE 2022
Country/TerritoryUnited States
CityPalo Alto
Period21/03/2223/03/22

Bibliographical note

Funding Information:
We would like to thank Wouter Beek and Rosaline de Haan from Triply, Amsterdam and Peter Bloem from the Vrije Universiteit Amsterdam, for the interesting discussions on this work and their overall support. The work presented here overlaps with the thesis of the first author.

Publisher Copyright:
© 2022 Copyright for this paper by its authors

Funding

We would like to thank Wouter Beek and Rosaline de Haan from Triply, Amsterdam and Peter Bloem from the Vrije Universiteit Amsterdam, for the interesting discussions on this work and their overall support. The work presented here overlaps with the thesis of the first author.

Keywords

  • Graph Neural Networks
  • Link Prediction
  • Machine Learning
  • Potential Energy

Fingerprint

Dive into the research topics of 'Potential Energy to Improve Link Prediction With Relational Graph Neural Networks'. Together they form a unique fingerprint.

Cite this