TY - GEN
T1 - Two Problems in Knowledge Graph Embedding
T2 - 2019 IEEE International Conference on Big Data, Big Data 2019
AU - Nur, Nasheen
AU - Park, Noseong
AU - Lee, Kookjin
AU - Kang, Hyunjoong
AU - Kwon, Soonhyeon
N1 - Funding Information:
This work was supported by the National Research Council of Science & Technology (NST) grant by the Korea government (MSIP) (No. CRC-15-05-ETRI). This paper describes objective technical results and analysis. Any subjective views or opinions that might be expressed in the paper do not necessarily represent the views of the U.S. Department of Energy or the United States Government Sandia National Laboratories is a multimission laboratory managed and operated by National Technology and Engineering Solutions of Sandia, LLC., a wholly owned subsidiary of Honeywell International, Inc., for the U.S. Department of Energys National Nuclear Security Administration under contract DE-NA-0003525. Noseong Park is the corresponding author.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Knowledge graph embedding (KGE) learns latent vector representations of named entities (i.e., vertices) and relations (i.e., edge labels) of knowledge graphs. Herein, we address two problems in KGE. First, relations may belong to one or multiple categories, such as functional, symmetric, transitive, reflexive, and so forth; thus, relation categories are not exclusive. Some relation categories cause non-trivial challenges for KGE. Second, we found that zero gradients happen frequently in many translation based embedding methods such as TransE and its variations. To solve these problems, we propose i) converting a knowledge graph into a bipartite graph, although we do not physically convert the graph but rather use an equivalent trick; ii) using multiple vector representations for a relation; and iii) using a new hinge loss based on energy ratio(rather than energy gap) that does not cause zero gradients. We show that our method significantly improves the quality of embedding.
AB - Knowledge graph embedding (KGE) learns latent vector representations of named entities (i.e., vertices) and relations (i.e., edge labels) of knowledge graphs. Herein, we address two problems in KGE. First, relations may belong to one or multiple categories, such as functional, symmetric, transitive, reflexive, and so forth; thus, relation categories are not exclusive. Some relation categories cause non-trivial challenges for KGE. Second, we found that zero gradients happen frequently in many translation based embedding methods such as TransE and its variations. To solve these problems, we propose i) converting a knowledge graph into a bipartite graph, although we do not physically convert the graph but rather use an equivalent trick; ii) using multiple vector representations for a relation; and iii) using a new hinge loss based on energy ratio(rather than energy gap) that does not cause zero gradients. We show that our method significantly improves the quality of embedding.
KW - Knowledge Graph
KW - Knowledge Graph Embedding
KW - Relational Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85081306061&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081306061&partnerID=8YFLogxK
U2 - 10.1109/BigData47090.2019.9005966
DO - 10.1109/BigData47090.2019.9005966
M3 - Conference contribution
AN - SCOPUS:85081306061
T3 - Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
SP - 1181
EP - 1186
BT - Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
A2 - Baru, Chaitanya
A2 - Huan, Jun
A2 - Khan, Latifur
A2 - Hu, Xiaohua Tony
A2 - Ak, Ronay
A2 - Tian, Yuanyuan
A2 - Barga, Roger
A2 - Zaniolo, Carlo
A2 - Lee, Kisung
A2 - Ye, Yanfang Fanny
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 December 2019 through 12 December 2019
ER -