mlsanityData to 14 Oct 2026

Negative Sampling in Knowledge Graph Representation Learning: A Review

arXiv 2402.19195 ↗First posted 29 Feb 2024cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Knowledge Graph Representation Learning (KGRL), or Knowledge Graph Embedding (KGE), is essential for AI applications such as knowledge construction and information retrieval. These models encode entities and relations into lower-dimensional vectors, supporting tasks like link prediction and recommendation systems. Training KGE models relies on both positive and negative samples for effective learning, but generating high-quality negative samples from existing knowledge graphs is challenging. The quality of these samples significantly impacts the model's accuracy. This comprehensive survey paper systematically reviews various negative sampling (NS) methods and their contributions to the success of KGRL. Their respective advantages and disadvantages are outlined by categorizing existing NS methods into six distinct categories. Moreover, this survey identifies open research questions that serve as potential directions for future investigations. By offering a generalization and alignment of fundamental NS concepts, this survey provides valuable insights for designing effective NS methods in the context of KGRL and serves as a motivating force for further advancements in the field.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 59 of its 139 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

59 of 139 references.

References · 59

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  8. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  9. 2016Complex Embeddings for Simple Link Predictioncited by 902
  10. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  11. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  12. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
38 more
  1. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 528
  2. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  3. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 343
  4. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  5. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  6. 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
  7. 2015Holographic Embeddings of Knowledge Graphscited by 181
  8. 2019Quaternion Knowledge Graph Embeddingscited by 175
  9. 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
  10. 2018DKN: Deep Knowledge-Aware Network for News Recommendationcited by 137
  11. 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
  12. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  13. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 119
  14. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 91
  15. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
  16. 2017Analogical Inference for Multi-Relational Embeddingscited by 69
  17. 2020Understanding Negative Sampling in Graph Representation Learningcited by 66
  18. 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
  19. 2019InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactionscited by 58
  20. 2018NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embeddingcited by 42
  21. 2019Interaction Embeddings for Prediction and Explanation in Knowledge Graphscited by 40
  22. 2017TorusE: Knowledge Graph Embedding on a Lie Groupcited by 36
  23. 2015Type-Constrained Representation Learning in Knowledge Graphscited by 34
  24. 2018Incorporating GAN for Negative Sampling in Knowledge Representation Learningcited by 31
  25. 2018A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalizationcited by 30
  26. 2015TransG : A Generative Mixture Model for Knowledge Graph Embeddingcited by 28
  27. 2021Inductive Relation Prediction by BERTcited by 27
  28. 2020Structure Aware Negative Sampling in Knowledge Graphscited by 26
  29. 2017Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphscited by 23
  30. 2020Inductive Learning on Commonsense Knowledge Graph Completioncited by 22
  31. 2015TransA: An Adaptive Approach for Knowledge Graph Embeddingcited by 19
  32. 2015From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Predictioncited by 19
  33. 2017An Interpretable Knowledge Transfer Model for Knowledge Base Completioncited by 17
  34. 2021Efficient Non-Sampling Knowledge Graph Embeddingcited by 14
  35. 2022CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completioncited by 13
  36. 2021Relation-aware Graph Attention Model With Adaptive Self-adversarial Trainingcited by 12
  37. 2021KGBoost: A Classification-based Knowledge Base Completion Method with Negative Samplingcited by 10
  38. 2023Negative Sampling with Adaptive Denoising Mixup for Knowledge Graph Embeddingcited by 7

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2025Diffusion-based Hierarchical Negative Sampling for Multimodal Knowledge Graph Completioncited by 1
  2. 2025T-TExTS (Teaching Text Expansion for Teacher Scaffolding): Enhancing Text Selection in High School Literature through Knowledge Graph-Based Recommendationcited by 1
  3. 2025Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Modelscited by 1
  4. 2024Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Modelscited by 0
  5. 2024Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completioncited by 0
  6. 2025A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospectscited by 0
  7. 2025Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendationcited by 0
  8. 2026PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEENcited by 0
  9. 2026ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Predictioncited by 0