# Distributional Negative Sampling for Knowledge Base Completion

arXiv: https://arxiv.org/abs/1908.06178 · HTML: https://mlsanity.com/paper/1908.06178/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings](https://mlsanity.com/paper/2203.04703/) (2022)
- [Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Models](https://mlsanity.com/paper/2508.05587/) (2025)
- [A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects](https://mlsanity.com/paper/2506.11012/) (2025)
- [PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN](https://mlsanity.com/paper/2608.30652/) (2026)

## Abstract (arXiv)

State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities. In this paper, we argue that random sampling is not a good training strategy since it is highly likely to generate a huge number of nonsensical assertions during training, which does not provide relevant training signal to the system. Hence, it slows down the learning process and decreases accuracy. To address this issue, we propose an alternative approach called Distributional Negative Sampling that generates meaningful negative examples which are highly likely to be false. Our approach achieves a significant improvement in Mean Reciprocal Rank values amongst two different KBC algorithms in three standard academic benchmarks.