TY - GEN
T1 - Efficient parallel translating embedding for knowledge graphs
AU - Zhang, Denghui
AU - Li, Manling
AU - Jia, Yantao
AU - Wang, Yuanzhuo
AU - Cheng, Xueqi
N1 - Publisher Copyright:
© 2017 ACM.
PY - 2017/8/23
Y1 - 2017/8/23
N2 - Knowledge graph embedding aims to embed entities and relations of knowledge graphs into low-dimensional vector spaces. Translating embedding methods regard relations as the translation from head entities to tail entities, which achieve the state-of-The-Art results among knowledge graph embedding methods. However, a major limitation of these methods is the time consuming training process, which may take several days or even weeks for large knowledge graphs, and result in great difficulty in practical applications. In this paper, we propose an effcient parallel framework for translating embedding methods, called ParTrans-X, which enables the methods to be paralleled without locks by utilizing the distinguished structures of knowledge graphs. Experiments on two datasets with three typical translating embedding methods, i.e., TransE [3], TransH [19], and a more efficient variant TransE- AdaGrad [11] validate that ParTrans-X can speed up the training process by more than an order of magnitude.
AB - Knowledge graph embedding aims to embed entities and relations of knowledge graphs into low-dimensional vector spaces. Translating embedding methods regard relations as the translation from head entities to tail entities, which achieve the state-of-The-Art results among knowledge graph embedding methods. However, a major limitation of these methods is the time consuming training process, which may take several days or even weeks for large knowledge graphs, and result in great difficulty in practical applications. In this paper, we propose an effcient parallel framework for translating embedding methods, called ParTrans-X, which enables the methods to be paralleled without locks by utilizing the distinguished structures of knowledge graphs. Experiments on two datasets with three typical translating embedding methods, i.e., TransE [3], TransH [19], and a more efficient variant TransE- AdaGrad [11] validate that ParTrans-X can speed up the training process by more than an order of magnitude.
KW - Knowledge graph embedding
KW - Parallel
KW - Translation-based
UR - http://www.scopus.com/inward/record.url?scp=85031047989&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85031047989&partnerID=8YFLogxK
U2 - 10.1145/3106426.3106447
DO - 10.1145/3106426.3106447
M3 - Conference contribution
AN - SCOPUS:85031047989
T3 - Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
SP - 460
EP - 468
BT - Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
T2 - 16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
Y2 - 23 August 2017 through 26 August 2017
ER -