HMNet: Hybrid Matching Network for Few-Shot Link Prediction

Shan Xiao, Lei Duan, Guicai Xie, Renhao Li, Zihao Chen, Geng Deng, Jyrki Nummenmaa

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


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.

Original languageEnglish
Title of host publicationDatabase Systems for Advanced Applications - 26th International Conference, DASFAA 2021, Proceedings
EditorsChristian S. Jensen, Ee-Peng Lim, De-Nian Yang, Wang-Chien Lee, Vincent S. Tseng, Vana Kalogeraki, Jen-Wei Huang, Chih-Ya Shen
Number of pages16
ISBN (Print)9783030731939
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventInternational Conference on Database Systems for Advanced Applications -
Duration: 11 Apr 202114 Apr 2021

Publication series

NameLecture Notes in Computer Science
Volume12681 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceInternational Conference on Database Systems for Advanced Applications


  • Feature attention mechanism
  • Few-shot link prediction
  • Hybrid matching network

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)


Dive into the research topics of 'HMNet: Hybrid Matching Network for Few-Shot Link Prediction'. Together they form a unique fingerprint.

Cite this