Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00321682" target="_blank" >RIV/68407700:21230/18:00321682 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.jair.org/index.php/jair/article/view/11203" target="_blank" >https://www.jair.org/index.php/jair/article/view/11203</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

Popis výsledku v původním jazyce

We propose a method to combine the interpretability and expressive power of firstorder logic with the effectiveness of neural network learning. In particular, we introduce a lifted framework in which first-order rules are used to describe the structure of a given problem setting. These rules are then used as a template for constructing a number of neural networks, one for each training and testing example. As the different networks corresponding to different examples share their weights, these weights can be efficiently learned using stochastic gradient descent. Our framework provides a flexible way for implementing and combining a wide variety of modelling constructs. In particular, the use of first-order logic allows for a declarative specification of latent relational structures, which can then be efficiently discovered in a given data set using neural network learning. Experiments on 78 relational learning benchmarks clearly demonstrate the effectiveness of the framework.

Název v anglickém jazyce

Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

Popis výsledku anglicky

We propose a method to combine the interpretability and expressive power of firstorder logic with the effectiveness of neural network learning. In particular, we introduce a lifted framework in which first-order rules are used to describe the structure of a given problem setting. These rules are then used as a template for constructing a number of neural networks, one for each training and testing example. As the different networks corresponding to different examples share their weights, these weights can be efficiently learned using stochastic gradient descent. Our framework provides a flexible way for implementing and combining a wide variety of modelling constructs. In particular, the use of first-order logic allows for a declarative specification of latent relational structures, which can then be efficiently discovered in a given data set using neural network learning. Experiments on 78 relational learning benchmarks clearly demonstrate the effectiveness of the framework.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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/GA17-26999S" target="_blank" >GA17-26999S: Hluboké relační učení</a><br>

Návaznosti

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

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název periodika

Journal of Artificial Intelligence Research

ISSN

1076-9757

e-ISSN

1943-5037

Svazek periodika

62

Číslo periodika v rámci svazku

May

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

32

Strana od-do

69-100

Kód UT WoS článku

000441027500003

EID výsledku v databázi Scopus

2-s2.0-85048052675