GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces
Knowledge graph embedding aims to construct a low-dimensional and continuous space, which is able to describe the semantics of high-dimensional and sparse knowledge graphs. Among existing solutions, translation models have drawn much attention lately, which use a relation vector to translate the hea...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8269287/ |
id |
doaj-a540710172254c85b729e59f59a6e980 |
---|---|
record_format |
Article |
spelling |
doaj-a540710172254c85b729e59f59a6e9802021-03-29T20:37:57ZengIEEEIEEE Access2169-35362018-01-0168232824410.1109/ACCESS.2018.27978768269287GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation SpacesZhen Tan0Xiang Zhao1https://orcid.org/0000-0001-6339-0219Yang Fang2Weidong Xiao3National University of Defense Technology, Changsha, ChinaNational University of Defense Technology, Changsha, ChinaNational University of Defense Technology, Changsha, ChinaNational University of Defense Technology, Changsha, ChinaKnowledge graph embedding aims to construct a low-dimensional and continuous space, which is able to describe the semantics of high-dimensional and sparse knowledge graphs. Among existing solutions, translation models have drawn much attention lately, which use a relation vector to translate the head entity vector, the result of which is close to the tail entity vector. Compared with classical embedding methods, translation models achieve the state-of-the-art performance; nonetheless, the rationale and mechanism behind them still aspire after understanding and investigation. In this connection, we quest into the essence of translation models, and present a generic model, namely, GTrans, to entail all the existing translation models. In GTrans, each entity is interpreted by a combination of two states-eigenstate and mimesis. Eigenstate represents the features that an entity intrinsically owns, and mimesis expresses the features that are affected by associated relations. The weighting of the two states can be tuned, and hence, dynamic and static weighting strategies are put forward to best describe entities in the problem domain. Besides, GTrans incorporates a dynamic relation space for each relation, which not only enables the flexibility of our model but also reduces the noise from other relation spaces. In experiments, we evaluate our proposed model with two benchmark tasks-triplets classification and link prediction. Experiment results witness significant and consistent performance gain that is offered by GTrans over existing alternatives.https://ieeexplore.ieee.org/document/8269287/Knowledge graph embeddingmulti-state entitiesdynamic relation spacestriplets classificationlink prediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhen Tan Xiang Zhao Yang Fang Weidong Xiao |
spellingShingle |
Zhen Tan Xiang Zhao Yang Fang Weidong Xiao GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces IEEE Access Knowledge graph embedding multi-state entities dynamic relation spaces triplets classification link prediction |
author_facet |
Zhen Tan Xiang Zhao Yang Fang Weidong Xiao |
author_sort |
Zhen Tan |
title |
GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces |
title_short |
GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces |
title_full |
GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces |
title_fullStr |
GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces |
title_full_unstemmed |
GTrans: Generic Knowledge Graph Embedding via Multi-State Entities and Dynamic Relation Spaces |
title_sort |
gtrans: generic knowledge graph embedding via multi-state entities and dynamic relation spaces |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Knowledge graph embedding aims to construct a low-dimensional and continuous space, which is able to describe the semantics of high-dimensional and sparse knowledge graphs. Among existing solutions, translation models have drawn much attention lately, which use a relation vector to translate the head entity vector, the result of which is close to the tail entity vector. Compared with classical embedding methods, translation models achieve the state-of-the-art performance; nonetheless, the rationale and mechanism behind them still aspire after understanding and investigation. In this connection, we quest into the essence of translation models, and present a generic model, namely, GTrans, to entail all the existing translation models. In GTrans, each entity is interpreted by a combination of two states-eigenstate and mimesis. Eigenstate represents the features that an entity intrinsically owns, and mimesis expresses the features that are affected by associated relations. The weighting of the two states can be tuned, and hence, dynamic and static weighting strategies are put forward to best describe entities in the problem domain. Besides, GTrans incorporates a dynamic relation space for each relation, which not only enables the flexibility of our model but also reduces the noise from other relation spaces. In experiments, we evaluate our proposed model with two benchmark tasks-triplets classification and link prediction. Experiment results witness significant and consistent performance gain that is offered by GTrans over existing alternatives. |
topic |
Knowledge graph embedding multi-state entities dynamic relation spaces triplets classification link prediction |
url |
https://ieeexplore.ieee.org/document/8269287/ |
work_keys_str_mv |
AT zhentan gtransgenericknowledgegraphembeddingviamultistateentitiesanddynamicrelationspaces AT xiangzhao gtransgenericknowledgegraphembeddingviamultistateentitiesanddynamicrelationspaces AT yangfang gtransgenericknowledgegraphembeddingviamultistateentitiesanddynamicrelationspaces AT weidongxiao gtransgenericknowledgegraphembeddingviamultistateentitiesanddynamicrelationspaces |
_version_ |
1724194457013714944 |