Understanding Negative Sampling in Knowledge Graph Embedding

Jing Qian*, Gangmin Li, Katie Atkinson, Yong Yue

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Knowledge graph embedding (KGE) is to project entities and relations of a knowledge graph (KG) into a low-dimensional vector space, which has made steady progress in recent years. Conventional KGE methods, especially translational distance-based models, are trained through discriminating positive samples from negative ones. Most KGs store only positive samples for space efficiency. Negative sampling thus plays a crucial role in encoding triples of a KG. The quality of generated negative samples has a direct impact on the performance of learnt knowledge representation in a myriad of downstream tasks, such as recommendation, link prediction and node classification. We summarize current negative sampling approaches in KGE into three categories, static distribution-based, dynamic distribution-based and custom cluster-based respectively. Based on this categorization we discuss the most prevalent existing approaches and their characteristics. It is a hope that this review can provide some guidelines for new thoughts about negative sampling in KGE.
Original languageEnglish
Pages (from-to)71
Number of pages11
JournalInternational Journal of Artificial Intelligence and Applications
Issue number1
Publication statusPublished - Jan 2021


  • Negative Sampling
  • Knowledge Graph Embedding
  • Generative Adversarial Network


Dive into the research topics of 'Understanding Negative Sampling in Knowledge Graph Embedding'. Together they form a unique fingerprint.

Cite this