# Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs

arXiv: https://arxiv.org/abs/1708.06816 · HTML: https://mlsanity.com/paper/1708.06816/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2017.

## Built on by (most cited first, 23 of 23)

- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation](https://mlsanity.com/paper/2106.05894/) (2021)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion](https://mlsanity.com/paper/2108.01387/) (2021)
- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction](https://mlsanity.com/paper/2303.00286/) (2023)
- [Kronecker Decomposition for Knowledge Graph Embeddings](https://mlsanity.com/paper/2205.06560/) (2022)
- [Pre-training Transformers for Knowledge Graph Completion](https://mlsanity.com/paper/2303.15682/) (2023)
- [TWIG: Towards pre-hoc Hyperparameter Optimisation and Cross-Graph Generalisation via Simulated KGE Models](https://mlsanity.com/paper/2402.06097/) (2024)
- [A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings](https://mlsanity.com/paper/2412.10092/) (2024)
- [Leveraging Wikidata's edit history in knowledge graph refinement tasks](https://mlsanity.com/paper/2210.15495/) (2022)
- [Counterfactual Reasoning with Knowledge Graph Embeddings](https://mlsanity.com/paper/2403.06936/) (2024)
- [Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Models](https://mlsanity.com/paper/2508.05587/) (2025)
- [Scaling Knowledge Graph Embedding Models](https://mlsanity.com/paper/2201.02791/) (2022)
- [A knowledge graph representation learning approach to predict novel kinase-substrate interactions](https://mlsanity.com/paper/2206.02290/) (2022)
- [Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Models](https://mlsanity.com/paper/2411.14858/) (2024)
- [Extending TWIG: Zero-Shot Predictive Hyperparameter Selection for KGEs based on Graph Structure](https://mlsanity.com/paper/2412.14801/) (2024)
- [Utilizing Graph Neural Networks for Effective Link Prediction in Microservice Architectures](https://mlsanity.com/paper/2501.15019/) (2025)
- [Improving Knowledge Graph Embeddings through Contrastive Learning with Negative Statements](https://mlsanity.com/paper/2510.11868/) (2025)
- [Plausibility-Driven Prioritization of Candidate Biomedical Annotations](https://mlsanity.com/paper/2607.20163/) (2026)
- [PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN](https://mlsanity.com/paper/2608.30652/) (2026)
- [HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs](https://mlsanity.com/paper/2609.02056/) (2026)
- [Uncertainty in Representation Learning on Knowledge Graphs](https://mlsanity.com/paper/2610.06974/) (2026)

## Abstract (arXiv)

Knowledge graphs are large, useful, but incomplete knowledge repositories. They encode knowledge through entities and relations which define each other through the connective structure of the graph. This has inspired methods for the joint embedding of entities and relations in continuous low-dimensional vector spaces, that can be used to induce new edges in the graph, i.e., link prediction in knowledge graphs. Learning these representations relies on contrasting positive instances with negative ones. Knowledge graphs include only positive relation instances, leaving the door open for a variety of methods for selecting negative examples. In this paper we present an empirical study on the impact of negative sampling on the learned embeddings, assessed through the task of link prediction. We use state-of-the-art knowledge graph embeddings -- rescal , TransE, DistMult and ComplEX -- and evaluate on benchmark datasets -- FB15k and WN18. We compare well known methods for negative sampling and additionally propose embedding based sampling methods. We note a marked difference in the impact of these sampling methods on the two datasets, with the "traditional" corrupting positives method leading to best results on WN18, while embedding based methods benefiting the task on FB15k.