# MixKG: Mixing for harder negative samples in knowledge graph

arXiv: https://arxiv.org/abs/2202.09606 · HTML: https://mlsanity.com/paper/2202.09606/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 19 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [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)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion](https://mlsanity.com/paper/1811.04441/) (2018)
- [KBGAN: Adversarial Learning for Knowledge Graph Embeddings](https://mlsanity.com/paper/1711.04071/) (2017)
- [SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup](https://mlsanity.com/paper/2010.02322/) (2020)
- [NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/1812.06410/) (2018)
- [SSMix: Saliency-Based Span Mixup for Text Classification](https://mlsanity.com/paper/2106.08062/) (2021)
- [Incorporating GAN for Negative Sampling in Knowledge Representation Learning](https://mlsanity.com/paper/1809.11017/) (2018)
- [Structure Aware Negative Sampling in Knowledge Graphs](https://mlsanity.com/paper/2009.11355/) (2020)
- [A survey of embedding models of entities and relationships for knowledge graph completion](https://mlsanity.com/paper/1703.08098/) (2017)

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

- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [Negative Sampling with Adaptive Denoising Mixup for Knowledge Graph Embedding](https://mlsanity.com/paper/2310.09781/) (2023)
- [LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings](https://mlsanity.com/paper/2203.04703/) (2022)
- [Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction](https://mlsanity.com/paper/2504.03327/) (2025)

## Abstract (arXiv)

Knowledge graph embedding~(KGE) aims to represent entities and relations into low-dimensional vectors for many real-world applications. The representations of entities and relations are learned via contrasting the positive and negative triplets. Thus, high-quality negative samples are extremely important in KGE. However, the present KGE models either rely on simple negative sampling methods, which makes it difficult to obtain informative negative triplets; or employ complex adversarial methods, which requires more training data and strategies. In addition, these methods can only construct negative triplets using the existing entities, which limits the potential to explore harder negative triplets. To address these issues, we adopt mixing operation in generating harder negative samples for knowledge graphs and introduce an inexpensive but effective method called MixKG. Technically, MixKG first proposes two kinds of criteria to filter hard negative triplets among the sampled negatives: based on scoring function and based on correct entity similarity. Then, MixKG synthesizes harder negative samples via the convex combinations of the paired selected hard negatives. Experiments on two public datasets and four classical KGE methods show MixKG is superior to previous negative sampling algorithms.