Facets (new session)
Description
Metadata
Settings
owl:sameAs
Inference Rule:
b3s
b3sifp
dbprdf-label
facets
http://dbpedia.org/resource/inference/rules/dbpedia#
http://dbpedia.org/resource/inference/rules/opencyc#
http://dbpedia.org/resource/inference/rules/umbel#
http://dbpedia.org/resource/inference/rules/yago#
http://dbpedia.org/schema/property_rules#
http://www.ontologyportal.org/inference/rules/SUMO#
http://www.ontologyportal.org/inference/rules/WordNet#
http://www.w3.org/2002/07/owl#
ldp
oplweb
skos-trans
virtrdf-label
None
About:
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
Goto
Sponge
NotDistinct
Permalink
An Entity of Type :
schema:ScholarlyArticle
, within Data Space :
covidontheweb.inria.fr
associated with source
document(s)
Type:
Academic Article
research paper
schema:ScholarlyArticle
New Facet based on Instances of this Class
Attributes
Values
type
Academic Article
research paper
schema:ScholarlyArticle
isDefinedBy
Covid-on-the-Web dataset
title
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
Creator
Korea, South
Hwang, Sung
Lee, Dong
Kaist,
Aitrics,
»more»
source
ArXiv
abstract
Many practical graph problems, such as knowledge graph construction and drug-to-drug interaction, require to handle multi-relational graphs. However, handling real-world multi-label graphs with Graph Neural Networks (GNNs) is often challenging due to their evolving nature, where new entities (nodes) can emerge over time. Moreover, newly emerged entities often have few links, which makes the learning even more difficult. Motivated by this challenge, we introduce a realistic problem of few-shot out-of-graph link prediction, where we not only predict the links between the seen and unseen nodes as in a conventional out-of-knowledge link prediction but also between the unseen nodes, with only few edges per node. We tackle this problem with a novel transductive meta-learning framework which we refer to as Graph Extrapolation Networks (GEN). GEN meta-learns both the node embedding network for inductive inference (seen-to-unseen) and the link prediction network for transductive inference (unseen-to-unseen). For transductive link prediction, we further propose a stochastic embedding layer to model uncertainty in the link prediction between unseen entities. We validate our model on multiple benchmark datasets for knowledge graph link prediction and drug-to-drug interaction prediction. The results show that our model significantly outperforms relevant baselines for out-of-graph link prediction tasks.
has issue date
2020-06-11
(
xsd:dateTime
)
has license
arxiv
sha1sum (hex)
225d571f97f9097be436626f225cff572007aaf4
resource representing a document's title
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
resource representing a document's body
covid:225d571f97f9097be436626f225cff572007aaf4#body_text
is
schema:about
of
named entity 'edges'
named entity 'tackle'
named entity 'embedding'
named entity 'nature'
named entity 'Networks'
»more»
◂◂ First
◂ Prev
Next ▸
Last ▸▸
Page 1 of 5
Go
Faceted Search & Find service v1.13.91 as of Mar 24 2020
Alternative Linked Data Documents:
Sponger
|
ODE
Content Formats:
RDF
ODATA
Microdata
About
OpenLink Virtuoso
version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software