TY - GEN
T1 - A structural representation learning for multi-relational networks
AU - Liu, Lin
AU - Li, Xin
AU - CHEUNG, Kwok Wai
AU - Xu, Chengcheng
N1 - Funding Information:
∗Corresponding Author: Xin Li (xinli@bit.edu.cn). This work has been partially supported by NSFC under Grant No. 61300178, National Program on Key Basic Research Project under Grant No. 2013CB329605.
PY - 2017/8
Y1 - 2017/8
N2 - Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations that significant triangular connectivity structures and parallelogram connectivity structures found in many real multi-relational networks are often ignored and that a hard-constraint commonly adopted by most of the network embedding methods is inaccurate by design, we propose a novel representation learning model for multi-relational networks which can alleviate both fundamental limitations. Scalable learning algorithms are derived using the stochastic gradient descent algorithm and negative sampling. Extensive experiments on real multi-relational network datasets of WordNet and Free-base demonstrate the efficacy of the proposed model when compared with the state-of-the-art embedding methods.
AB - Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations that significant triangular connectivity structures and parallelogram connectivity structures found in many real multi-relational networks are often ignored and that a hard-constraint commonly adopted by most of the network embedding methods is inaccurate by design, we propose a novel representation learning model for multi-relational networks which can alleviate both fundamental limitations. Scalable learning algorithms are derived using the stochastic gradient descent algorithm and negative sampling. Extensive experiments on real multi-relational network datasets of WordNet and Free-base demonstrate the efficacy of the proposed model when compared with the state-of-the-art embedding methods.
KW - Natural Language Processing
KW - Information Extraction
KW - Information Retrieval
KW - Machine Learning
KW - Multi-instance/Multi-label/Multi-view learning
KW - Knowledge-based Learning
UR - http://www.scopus.com/inward/record.url?scp=85031912795&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2017/565
DO - 10.24963/ijcai.2017/565
M3 - Conference contribution
AN - SCOPUS:85031912795
SN - 9780999241103
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 4047
EP - 4053
BT - Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, (IJCAI-17)
A2 - Sierra, Carles
PB - AAAI press
T2 - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Y2 - 19 August 2017 through 25 August 2017
ER -