About: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
Creator	Kalousis, Alexandros Kiritsis, Dimitris Kolyvakis, Prodromos
Source	PMC
abstract	Learning embeddings of entities and relations existing in knowledge bases allows the discovery of hidden patterns in them. In this work, we examine the contribution of geometrical space to the task of knowledge base completion. We focus on the family of translational models, whose performance has been lagging. We extend these models to the hyperbolic space so as to better reflect the topological properties of knowledge bases. We investigate the type of regularities that our model, dubbed HyperKG, can capture and show that it is a prominent candidate for effectively representing a subset of Datalog rules. We empirically show, using a variety of link prediction datasets, that hyperbolic space allows to narrow down significantly the performance gap between translational and bilinear models and effectively represent certain types of rules. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this chapter (10.1007/978-3-030-49461-2_12) contains supplementary material, which is available to authorized users.
has issue date	2020-05-07(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49461-2_12
has license	no-cc
sha1sum (hex)	cb33c7bc770f1911087f6d7aec3c37031040c10f
schema:url	https://doi.org/10.1007/978-3-030-49461-2_12
resource representing a document's title	Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
has PubMed Central identifier	PMC7250606
schema:publication	The Semantic Web
resource representing a document's body	covid:cb33c7bc770f1911087f6d7aec3c37031040c10f#body_text
is schema:about of	named entity 'FAMILY' named entity 'EXTEND' named entity 'THESE' named entity 'MODEL' named entity 'GAP' named entity 'hyperbolic space' named entity 'Knowledge Graph' named entity 'loss function' named entity 'KBs' named entity 'knowledge base' named entity 'permutation matrix' named entity 'vectors' named entity 'vectors' named entity 'power-law' named entity 'power-law distribution' named entity 'hyperbolic space' named entity 'circular permutation' named entity 'ontological' named entity 'logical consistency' named entity 'KBs' named entity 'hyperbolic space' named entity 'asymmetric relations' named entity 'training set' named entity 'loss function' named entity 'vector' named entity 'Matrix-vector multiplication' named entity 'Kiela' named entity 'finite set' named entity 'Riemannian manifolds' named entity 'Hyperbolic geometry' named entity 'focus on the family' named entity 'cardinalities' named entity 'subsumption' named entity 'activation function' named entity 'ontology' named entity 'iff' named entity 'permutation matrix' named entity 'histogram' named entity 'scale-free' named entity 'hyperbolic space' named entity 'hyperbolic geometry' named entity 'KBs' named entity 'vector' named entity 'geometrical space' named entity 'subset' named entity 'orthogonal' named entity 'Euclidean space' named entity 'orthogonal matrix' named entity 'disjoint sets' named entity 'Orthogonal matrices' named entity 'and/or' named entity 'scale-free' named entity 'atom' named entity 'subset' named entity 'naturally emerge' named entity 'vector fields' named entity 'question answering' named entity 'subset' named entity 'knowledge base' named entity 'and/or' named entity 'Suzuki' named entity 'ontology' named entity 'Moby Dick' named entity 'MRR' named entity 'distributed representations' named entity 'topological properties' named entity 'inductive reasoning' named entity 'Nickel' named entity 'KBs' named entity 'vector' named entity 'hyperbolic space' named entity 'KBs' named entity 'knowledge graphs' named entity 'numerical stability' named entity 'MRR' named entity 'vector representations' named entity 'rectifier' named entity 'KBs' named entity 'YAGO' named entity 'scale-free networks' named entity 'entities and relations'

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 © 2009-2024 OpenLink Software