Lifted Relational Neural Networks: from Graphs to Deep Relational Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00361162" target="_blank" >RIV/68407700:21230/23:00361162 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.3233/FAIA230147" target="_blank" >https://doi.org/10.3233/FAIA230147</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3233/FAIA230147" target="_blank" >10.3233/FAIA230147</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Lifted Relational Neural Networks: from Graphs to Deep Relational Learning

Popis výsledku v původním jazyce

Lifted Relational Neural Networks (LRNNs) were introduced in 2015 as a framework for combining logic programming with neural networks for efficient learning of latent relational structures, such as various subgraph patterns in molecules. In this chapter, we will briefly re-introduce the framework and explain its current relevance in the context of contemporary Graph Neural Networks (GNNs). Particularly, we will detail how the declarative nature of differentiable logic programming in LRNNs can be used to elegantly capture various GNN variants and generalize to novel, even more expressive, deep relational learning concepts. Additionally, we will briefly demonstrate practical use and computation performance of the framework.

Název v anglickém jazyce

Lifted Relational Neural Networks: from Graphs to Deep Relational Learning

Popis výsledku anglicky

Lifted Relational Neural Networks (LRNNs) were introduced in 2015 as a framework for combining logic programming with neural networks for efficient learning of latent relational structures, such as various subgraph patterns in molecules. In this chapter, we will briefly re-introduce the framework and explain its current relevance in the context of contemporary Graph Neural Networks (GNNs). Particularly, we will detail how the declarative nature of differentiable logic programming in LRNNs can be used to elegantly capture various GNN variants and generalize to novel, even more expressive, deep relational learning concepts. Additionally, we will briefly demonstrate practical use and computation performance of the framework.

Druh

C - Kapitola v odborné knize

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

A Compendium of Neuro-Symbolic Artificial Intelligence

ISBN

978-1-64368-406-2

Počet stran výsledku

29

Strana od-do

308-336

Počet stran knihy

694

Název nakladatele

IOS Press

Místo vydání

Amsterdam

Kód UT WoS kapitoly

—