# Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction

arXiv: https://arxiv.org/abs/2504.03327 · HTML: https://mlsanity.com/paper/2504.03327/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 69 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 30 of 39)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (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)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [A Survey on Knowledge Graph-Based Recommender Systems](https://mlsanity.com/paper/2003.00911/) (2020)
- [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018)
- [Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction](https://mlsanity.com/paper/1911.09419/) (2019)
- [BoxE: A Box Embedding Model for Knowledge Base Completion](https://mlsanity.com/paper/2007.06267/) (2020)
- [Sequence-to-Sequence Knowledge Graph Completion and Question Answering](https://mlsanity.com/paper/2203.10321/) (2022)
- [Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling](https://mlsanity.com/paper/1906.07241/) (2019)
- [Understanding Negative Sampling in Graph Representation Learning](https://mlsanity.com/paper/2005.09863/) (2020)
- [KBGAN: Adversarial Learning for Knowledge Graph Embeddings](https://mlsanity.com/paper/1711.04071/) (2017)
- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs](https://mlsanity.com/paper/2206.04798/) (2022)
- [NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/1812.06410/) (2018)
- [MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition](https://mlsanity.com/paper/2102.12664/) (2021)
- [Leveraging Knowledge Bases in LSTMs for Improving Machine Reading](https://mlsanity.com/paper/1902.09091/) (2019)
- [AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning](https://mlsanity.com/paper/2205.15319/) (2022)

## Built on by (most cited first, 1 of 1)

- [FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/2608.23849/) (2026)

## Abstract (arXiv)

Knowledge graph embedding (KGE) models encode the structural information of knowledge graphs to predicting new links. Effective training of these models requires distinguishing between positive and negative samples with high precision. Although prior research has shown that improving the quality of negative samples can significantly enhance model accuracy, identifying high-quality negative samples remains a challenging problem. This paper theoretically investigates the condition under which negative samples lead to optimal KG embedding and identifies a sufficient condition for an effective negative sample distribution. Based on this theoretical foundation, we propose Embedding MUtation (textscEMU), a novel framework that generates negative samples satisfying this condition, in contrast to conventional methods that focus on identifying challenging negative samples within the training data. Importantly, the simplicity of textscEMU ensures seamless integration with existing KGE models and negative sampling methods. To evaluate its efficacy, we conducted comprehensive experiments across multiple datasets. The results consistently demonstrate significant improvements in link prediction performance across various KGE models and negative sampling methods. Notably, textscEMU enables performance improvements comparable to those achieved by models with embedding dimension five times larger. An implementation of the method and experiments are available at https://github.com/nec-research/EMU-KG.