Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-hop neighbor information to enhance its semantic representation. Howev...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Niu, Guanglin Li, Yang Tang, Chengguang Geng, Ruiying Dai, Jian Liu, Qiao Wang, Hao Sun, Jian Huang, Fei Si, Luo |
description | Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs),
few-shot knowledge graph completion (FKGC) has recently gained more research
interests. Some existing models employ a few-shot relation's multi-hop neighbor
information to enhance its semantic representation. However, noise neighbor
information might be amplified when the neighborhood is excessively sparse and
no neighbor is available to represent the few-shot relation. Moreover, modeling
and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and
many-to-many (N-N) by previous knowledge graph completion approaches requires
high model complexity and a large amount of training instances. Thus, inferring
complex relations in the few-shot scenario is difficult for FKGC models due to
limited training instances. In this paper, we propose a few-shot relational
learning with global-local framework to address the above issues. At the global
stage, a novel gated and attentive neighbor aggregator is built for accurately
integrating the semantics of a few-shot relation's neighborhood, which helps
filtering the noise neighbors even if a KG contains extremely sparse
neighborhoods. For the local stage, a meta-learning based TransH (MTransH)
method is designed to model complex relations and train our model in a few-shot
learning fashion. Extensive experiments show that our model outperforms the
state-of-the-art FKGC approaches on the frequently-used benchmark datasets
NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model
achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on
Wiki-One by the metric Hits@10. |
doi_str_mv | 10.48550/arxiv.2104.13095 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2104_13095</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2104_13095</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-5a66aa40bc28ccdd664a3c8d7f7c092e2d67e672323dd73869e0be9b555a43383</originalsourceid><addsrcrecordid>eNotj8FOhDAURbtxYUY_wJX9AbC0tIUlIQ4aJ2OisycP-ihNmEJqM-jfOzO6uDl3dZJDyEPG0ryQkj1B-HanlGcsTzPBSnlLxg-cILrZw0R3CME7b-nq4kgbiGgoeEOrGNFHd0K6R2fHbg60sjaghXi-w3lbXJPPcY70zc_rhMYibQIsI63n4zLhxX9HbgaYvvD-nxty2D4f6pdk99681tUuAaVlIkEpgJx1PS_63hilchB9YfSge1Zy5EZpVJoLLozRolAlsg7LTkoJuRCF2JDHP-01tV2CO0L4aS_J7TVZ_ALMHVJE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion</title><source>arXiv.org</source><creator>Niu, Guanglin ; Li, Yang ; Tang, Chengguang ; Geng, Ruiying ; Dai, Jian ; Liu, Qiao ; Wang, Hao ; Sun, Jian ; Huang, Fei ; Si, Luo</creator><creatorcontrib>Niu, Guanglin ; Li, Yang ; Tang, Chengguang ; Geng, Ruiying ; Dai, Jian ; Liu, Qiao ; Wang, Hao ; Sun, Jian ; Huang, Fei ; Si, Luo</creatorcontrib><description>Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs),
few-shot knowledge graph completion (FKGC) has recently gained more research
interests. Some existing models employ a few-shot relation's multi-hop neighbor
information to enhance its semantic representation. However, noise neighbor
information might be amplified when the neighborhood is excessively sparse and
no neighbor is available to represent the few-shot relation. Moreover, modeling
and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and
many-to-many (N-N) by previous knowledge graph completion approaches requires
high model complexity and a large amount of training instances. Thus, inferring
complex relations in the few-shot scenario is difficult for FKGC models due to
limited training instances. In this paper, we propose a few-shot relational
learning with global-local framework to address the above issues. At the global
stage, a novel gated and attentive neighbor aggregator is built for accurately
integrating the semantics of a few-shot relation's neighborhood, which helps
filtering the noise neighbors even if a KG contains extremely sparse
neighborhoods. For the local stage, a meta-learning based TransH (MTransH)
method is designed to model complex relations and train our model in a few-shot
learning fashion. Extensive experiments show that our model outperforms the
state-of-the-art FKGC approaches on the frequently-used benchmark datasets
NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model
achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on
Wiki-One by the metric Hits@10.</description><identifier>DOI: 10.48550/arxiv.2104.13095</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2021-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2104.13095$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2104.13095$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Niu, Guanglin</creatorcontrib><creatorcontrib>Li, Yang</creatorcontrib><creatorcontrib>Tang, Chengguang</creatorcontrib><creatorcontrib>Geng, Ruiying</creatorcontrib><creatorcontrib>Dai, Jian</creatorcontrib><creatorcontrib>Liu, Qiao</creatorcontrib><creatorcontrib>Wang, Hao</creatorcontrib><creatorcontrib>Sun, Jian</creatorcontrib><creatorcontrib>Huang, Fei</creatorcontrib><creatorcontrib>Si, Luo</creatorcontrib><title>Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion</title><description>Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs),
few-shot knowledge graph completion (FKGC) has recently gained more research
interests. Some existing models employ a few-shot relation's multi-hop neighbor
information to enhance its semantic representation. However, noise neighbor
information might be amplified when the neighborhood is excessively sparse and
no neighbor is available to represent the few-shot relation. Moreover, modeling
and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and
many-to-many (N-N) by previous knowledge graph completion approaches requires
high model complexity and a large amount of training instances. Thus, inferring
complex relations in the few-shot scenario is difficult for FKGC models due to
limited training instances. In this paper, we propose a few-shot relational
learning with global-local framework to address the above issues. At the global
stage, a novel gated and attentive neighbor aggregator is built for accurately
integrating the semantics of a few-shot relation's neighborhood, which helps
filtering the noise neighbors even if a KG contains extremely sparse
neighborhoods. For the local stage, a meta-learning based TransH (MTransH)
method is designed to model complex relations and train our model in a few-shot
learning fashion. Extensive experiments show that our model outperforms the
state-of-the-art FKGC approaches on the frequently-used benchmark datasets
NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model
achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on
Wiki-One by the metric Hits@10.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FOhDAURbtxYUY_wJX9AbC0tIUlIQ4aJ2OisycP-ihNmEJqM-jfOzO6uDl3dZJDyEPG0ryQkj1B-HanlGcsTzPBSnlLxg-cILrZw0R3CME7b-nq4kgbiGgoeEOrGNFHd0K6R2fHbg60sjaghXi-w3lbXJPPcY70zc_rhMYibQIsI63n4zLhxX9HbgaYvvD-nxty2D4f6pdk99681tUuAaVlIkEpgJx1PS_63hilchB9YfSge1Zy5EZpVJoLLozRolAlsg7LTkoJuRCF2JDHP-01tV2CO0L4aS_J7TVZ_ALMHVJE</recordid><startdate>20210427</startdate><enddate>20210427</enddate><creator>Niu, Guanglin</creator><creator>Li, Yang</creator><creator>Tang, Chengguang</creator><creator>Geng, Ruiying</creator><creator>Dai, Jian</creator><creator>Liu, Qiao</creator><creator>Wang, Hao</creator><creator>Sun, Jian</creator><creator>Huang, Fei</creator><creator>Si, Luo</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210427</creationdate><title>Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion</title><author>Niu, Guanglin ; Li, Yang ; Tang, Chengguang ; Geng, Ruiying ; Dai, Jian ; Liu, Qiao ; Wang, Hao ; Sun, Jian ; Huang, Fei ; Si, Luo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-5a66aa40bc28ccdd664a3c8d7f7c092e2d67e672323dd73869e0be9b555a43383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Niu, Guanglin</creatorcontrib><creatorcontrib>Li, Yang</creatorcontrib><creatorcontrib>Tang, Chengguang</creatorcontrib><creatorcontrib>Geng, Ruiying</creatorcontrib><creatorcontrib>Dai, Jian</creatorcontrib><creatorcontrib>Liu, Qiao</creatorcontrib><creatorcontrib>Wang, Hao</creatorcontrib><creatorcontrib>Sun, Jian</creatorcontrib><creatorcontrib>Huang, Fei</creatorcontrib><creatorcontrib>Si, Luo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Niu, Guanglin</au><au>Li, Yang</au><au>Tang, Chengguang</au><au>Geng, Ruiying</au><au>Dai, Jian</au><au>Liu, Qiao</au><au>Wang, Hao</au><au>Sun, Jian</au><au>Huang, Fei</au><au>Si, Luo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion</atitle><date>2021-04-27</date><risdate>2021</risdate><abstract>Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs),
few-shot knowledge graph completion (FKGC) has recently gained more research
interests. Some existing models employ a few-shot relation's multi-hop neighbor
information to enhance its semantic representation. However, noise neighbor
information might be amplified when the neighborhood is excessively sparse and
no neighbor is available to represent the few-shot relation. Moreover, modeling
and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and
many-to-many (N-N) by previous knowledge graph completion approaches requires
high model complexity and a large amount of training instances. Thus, inferring
complex relations in the few-shot scenario is difficult for FKGC models due to
limited training instances. In this paper, we propose a few-shot relational
learning with global-local framework to address the above issues. At the global
stage, a novel gated and attentive neighbor aggregator is built for accurately
integrating the semantics of a few-shot relation's neighborhood, which helps
filtering the noise neighbors even if a KG contains extremely sparse
neighborhoods. For the local stage, a meta-learning based TransH (MTransH)
method is designed to model complex relations and train our model in a few-shot
learning fashion. Extensive experiments show that our model outperforms the
state-of-the-art FKGC approaches on the frequently-used benchmark datasets
NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model
achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on
Wiki-One by the metric Hits@10.</abstract><doi>10.48550/arxiv.2104.13095</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2104.13095 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2104_13095 |
source | arXiv.org |
subjects | Computer Science - Artificial Intelligence Computer Science - Computation and Language |
title | Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T07%3A25%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Relational%20Learning%20with%20Gated%20and%20Attentive%20Neighbor%20Aggregator%20for%20Few-Shot%20Knowledge%20Graph%20Completion&rft.au=Niu,%20Guanglin&rft.date=2021-04-27&rft_id=info:doi/10.48550/arxiv.2104.13095&rft_dat=%3Carxiv_GOX%3E2104_13095%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |