Sample and feature enhanced few-shot knowledge graph completion

Kai Zhang, Daokun Zhang, Ning Liu, Yonghua Yang, Yonghui Xu, Hui Li, Lizhen Cui

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


Knowledge graph completion is to infer missing/new entities or relations in knowledge graphs. The long-tail distribution of relations leads to the few-shot knowledge graph completion problem. Existing solutions do not thoroughly solve this problem, with the few training samples still deteriorating knowledge graph completion performance. In this paper, we propose a novel data augmentation mechanism to overcome the learning difficulty caused by few training samples, and a novel feature fusion scheme to reinforce data augmentation. Specifically, we use a conditional generative model to increase the number of entity samples on both entity structure and textual content views, and adaptively fuse entity structural and textual features to get informative entity representations. We then integrate adaptive feature fusion and generative sample augmentation with few-shot relation inference into an end-to-end learning framework. We conduct extensive experiments on five real-world knowledge graphs, showing the significant advantage of the proposed algorithm over state-of-the-art baselines, as well as the effectiveness of the proposed feature fusion and sample augmentation components.

Original languageEnglish
Title of host publication28th International Conference, DASFAA 2023 Tianjin, China, April 17–20, 2023 Proceedings, Part II
EditorsXin Wang, Maria Luisa Sapino, Wook-Shin Han, Amr El Abbadi, Gill Dobbie, Zhiyong Feng, Yingxiao Shao, Hongzhi Yin
Place of PublicationCham Switzerland
Number of pages10
ISBN (Electronic)9783031306723
ISBN (Print)9783031306716
Publication statusPublished - 2023
EventDatabase Systems for Advanced Applications 2023 - Tianjin, China
Duration: 17 Apr 202320 Apr 2023 (Peroceedings) (Website)

Publication series

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


ConferenceDatabase Systems for Advanced Applications 2023
Abbreviated titleDASFAA 2023
Internet address


  • Data Augmentation
  • Feature Fusion
  • Few-Shot Learning
  • Knowledge Graph Completion

Cite this