Learning with Molecules beyond Graph Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00347311" target="_blank" >RIV/68407700:21230/20:00347311 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/22:00356307

Výsledek na webu

<a href="https://ml4molecules.github.io/papers2020/ML4Molecules_2020_paper_24.pdf" target="_blank" >https://ml4molecules.github.io/papers2020/ML4Molecules_2020_paper_24.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Learning with Molecules beyond Graph Neural Networks

Popis výsledku v původním jazyce

In this paper we demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how GNNs and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic. The declarative nature of the used language then allows to easily modify and extend the propagation schemes into complex structures, such as the molecular rings which we choose for a short demonstration in this paper.

Název v anglickém jazyce

Learning with Molecules beyond Graph Neural Networks

Popis výsledku anglicky

In this paper we demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how GNNs and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic. The declarative nature of the used language then allows to easily modify and extend the propagation schemes into complex structures, such as the molecular rings which we choose for a short demonstration in this paper.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GJ20-19104Y" target="_blank" >GJ20-19104Y: Generativní relační modely</a><br>

Návaznosti

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

Rok uplatnění

2020

Kód důvěrnosti údajů

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