# Negative Sampling with Adaptive Denoising Mixup for Knowledge Graph Embedding

arXiv: https://arxiv.org/abs/2310.09781 · HTML: https://mlsanity.com/paper/2310.09781/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 15 Oct 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction](https://mlsanity.com/paper/1911.09419/) (2019)
- [On Mixup Regularization](https://mlsanity.com/paper/2006.06049/) (2020)
- [KBGAN: Adversarial Learning for Knowledge Graph Embeddings](https://mlsanity.com/paper/1711.04071/) (2017)
- [Incremental False Negative Detection for Contrastive Learning](https://mlsanity.com/paper/2106.03719/) (2021)
- [NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/1812.06410/) (2018)
- [Incorporating GAN for Negative Sampling in Knowledge Representation Learning](https://mlsanity.com/paper/1809.11017/) (2018)
- [GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2010.01447/) (2020)
- [Structure Aware Negative Sampling in Knowledge Graphs](https://mlsanity.com/paper/2009.11355/) (2020)
- [Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion](https://mlsanity.com/paper/1909.11359/) (2019)
- [CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion](https://mlsanity.com/paper/2202.13785/) (2022)
- [MixKG: Mixing for harder negative samples in knowledge graph](https://mlsanity.com/paper/2202.09606/) (2022)

## Built on by (most cited first, 7 of 7)

- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion](https://mlsanity.com/paper/2406.18166/) (2024)
- [Personalized Negative Reservoir for Incremental Learning in Recommender Systems](https://mlsanity.com/paper/2403.03993/) (2024)
- [Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction](https://mlsanity.com/paper/2504.03327/) (2025)
- [Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Models](https://mlsanity.com/paper/2508.05587/) (2025)
- [Are We Wasting Time? A Fast, Accurate Performance Evaluation Framework for Knowledge Graph Link Predictors](https://mlsanity.com/paper/2402.00053/) (2024)
- [PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN](https://mlsanity.com/paper/2608.30652/) (2026)

## Abstract (arXiv)

Knowledge graph embedding (KGE) aims to map entities and relations of a knowledge graph (KG) into a low-dimensional and dense vector space via contrasting the positive and negative triples. In the training process of KGEs, negative sampling is essential to find high-quality negative triples since KGs only contain positive triples. Most existing negative sampling methods assume that non-existent triples with high scores are high-quality negative triples. However, negative triples sampled by these methods are likely to contain noise. Specifically, they ignore that non-existent triples with high scores might also be true facts due to the incompleteness of KGs, which are usually called false negative triples. To alleviate the above issue, we propose an easily pluggable denoising mixup method called DeMix, which generates high-quality triples by refining sampled negative triples in a self-supervised manner. Given a sampled unlabeled triple, DeMix firstly classifies it into a marginal pseudo-negative triple or a negative triple based on the judgment of the KGE model itself. Secondly, it selects an appropriate mixup partner for the current triple to synthesize a partially positive or a harder negative triple. Experimental results on the knowledge graph completion task show that the proposed DeMix is superior to other negative sampling techniques, ensuring corresponding KGEs a faster convergence and better link prediction results.