TY - GEN
T1 - HMNet
T2 - International Conference on Database Systems for Advanced Applications
AU - Xiao, Shan
AU - Duan, Lei
AU - Xie, Guicai
AU - Li, Renhao
AU - Chen, Zihao
AU - Deng, Geng
AU - Nummenmaa, Jyrki
N1 - jufoid=62555
PY - 2021
Y1 - 2021
N2 - Knowledge graphs (KGs) are widely used in many real-world applications, such as information retrieval, question answering system, and personal recommendation. However, most KGs are suffering from the incompleteness problem. To deal with the task of link prediction, previous knowledge graph embedding methods require numerous reference instances for each relation. It is worth noting that most relations in KGs have only a few reference instances available. Existing works for few-shot link prediction evaluate the authenticity of triplets from a single relation perspective. In this paper, we propose Hybrid Matching Network (HMNet) for few-shot link prediction, evaluating triplets from entity and relation two perspectives. At the entity-aware matching network, HMNet uses attentive inductive embedding layer to aggregate entity features and relation-aware topology, and then provides entity-aware score to implement first perspective evaluation. At the relation-aware matching network, HMNet integrates feature attention mechanism to implement relation perspective evaluation. Experiments on two public datasets indicate that HMNet achieves promising performance in few-shot link prediction.
AB - Knowledge graphs (KGs) are widely used in many real-world applications, such as information retrieval, question answering system, and personal recommendation. However, most KGs are suffering from the incompleteness problem. To deal with the task of link prediction, previous knowledge graph embedding methods require numerous reference instances for each relation. It is worth noting that most relations in KGs have only a few reference instances available. Existing works for few-shot link prediction evaluate the authenticity of triplets from a single relation perspective. In this paper, we propose Hybrid Matching Network (HMNet) for few-shot link prediction, evaluating triplets from entity and relation two perspectives. At the entity-aware matching network, HMNet uses attentive inductive embedding layer to aggregate entity features and relation-aware topology, and then provides entity-aware score to implement first perspective evaluation. At the relation-aware matching network, HMNet integrates feature attention mechanism to implement relation perspective evaluation. Experiments on two public datasets indicate that HMNet achieves promising performance in few-shot link prediction.
KW - Feature attention mechanism
KW - Few-shot link prediction
KW - Hybrid matching network
U2 - 10.1007/978-3-030-73194-6_21
DO - 10.1007/978-3-030-73194-6_21
M3 - Conference contribution
AN - SCOPUS:85104732581
SN - 9783030731939
T3 - Lecture Notes in Computer Science
SP - 307
EP - 322
BT - Database Systems for Advanced Applications - 26th International Conference, DASFAA 2021, Proceedings
A2 - Jensen, Christian S.
A2 - Lim, Ee-Peng
A2 - Yang, De-Nian
A2 - Lee, Wang-Chien
A2 - Tseng, Vincent S.
A2 - Kalogeraki, Vana
A2 - Huang, Jen-Wei
A2 - Shen, Chih-Ya
PB - Springer
Y2 - 11 April 2021 through 14 April 2021
ER -