Cargando…

Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer

Knowledge graph completion (KGC) aims to predict missing information in a knowledge graph. Many existing embedding-based KGC models solve the Out-of-knowledge-graph (OOKG) entity problem (also known as zero-shot entity problem) by utilizing textual information resources such as descriptions and type...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Ming, Jia, Weijia, Huang, Yusheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7206237/
http://dx.doi.org/10.1007/978-3-030-47436-2_41
_version_ 1783530374788284416
author Zhao, Ming
Jia, Weijia
Huang, Yusheng
author_facet Zhao, Ming
Jia, Weijia
Huang, Yusheng
author_sort Zhao, Ming
collection PubMed
description Knowledge graph completion (KGC) aims to predict missing information in a knowledge graph. Many existing embedding-based KGC models solve the Out-of-knowledge-graph (OOKG) entity problem (also known as zero-shot entity problem) by utilizing textual information resources such as descriptions and types. However, few works utilize the extra structural information to generate embeddings. In this paper, we propose a new zero-shot scenario: how to acquire the embedding vector of a relation that is not observed at training time. Our work uses a convolutional transition and attention-based aggregation graph neural network to solve both the OOKG entity problem and the new OOKG relation problem without retraining, regarding the structural neighbors as the auxiliary information. The experimental results show the effectiveness of our proposed models in solving the OOKG relation problem. For the OOKG entity problem, our model performs better than the previous GNN-based model by 23.9% in NELL-995-Tail dataset.
format Online
Article
Text
id pubmed-7206237
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-72062372020-05-08 Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer Zhao, Ming Jia, Weijia Huang, Yusheng Advances in Knowledge Discovery and Data Mining Article Knowledge graph completion (KGC) aims to predict missing information in a knowledge graph. Many existing embedding-based KGC models solve the Out-of-knowledge-graph (OOKG) entity problem (also known as zero-shot entity problem) by utilizing textual information resources such as descriptions and types. However, few works utilize the extra structural information to generate embeddings. In this paper, we propose a new zero-shot scenario: how to acquire the embedding vector of a relation that is not observed at training time. Our work uses a convolutional transition and attention-based aggregation graph neural network to solve both the OOKG entity problem and the new OOKG relation problem without retraining, regarding the structural neighbors as the auxiliary information. The experimental results show the effectiveness of our proposed models in solving the OOKG relation problem. For the OOKG entity problem, our model performs better than the previous GNN-based model by 23.9% in NELL-995-Tail dataset. 2020-04-17 /pmc/articles/PMC7206237/ http://dx.doi.org/10.1007/978-3-030-47436-2_41 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Zhao, Ming
Jia, Weijia
Huang, Yusheng
Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer
title Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer
title_full Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer
title_fullStr Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer
title_full_unstemmed Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer
title_short Attention-Based Aggregation Graph Networks for Knowledge Graph Information Transfer
title_sort attention-based aggregation graph networks for knowledge graph information transfer
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7206237/
http://dx.doi.org/10.1007/978-3-030-47436-2_41
work_keys_str_mv AT zhaoming attentionbasedaggregationgraphnetworksforknowledgegraphinformationtransfer
AT jiaweijia attentionbasedaggregationgraphnetworksforknowledgegraphinformationtransfer
AT huangyusheng attentionbasedaggregationgraphnetworksforknowledgegraphinformationtransfer