# Toward Degree Bias in Embedding-Based Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2302.05044 · HTML: https://mlsanity.com/paper/2302.05044/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 10 Feb 2023.

## Builds on (most cited first, 30 of 36)

- [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)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [Data Augmentation Can Improve Robustness](https://mlsanity.com/paper/2111.05328/) (2021)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [On Calibration and Out-of-domain Generalization](https://mlsanity.com/paper/2102.10395/) (2021)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [CoDEx: A Comprehensive Knowledge Graph Completion Benchmark](https://mlsanity.com/paper/2009.07810/) (2020)
- [Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences](https://mlsanity.com/paper/1902.06236/) (2019)
- [Knowledge Graph Embedding for Link Prediction: A Comparative Analysis](https://mlsanity.com/paper/2002.00819/) (2020)
- [On Mixup Regularization](https://mlsanity.com/paper/2006.06049/) (2020)
- [Graph Data Augmentation for Graph Machine Learning: A Survey](https://mlsanity.com/paper/2202.08871/) (2022)

## Built on by (most cited first, 17 of 17)

- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction](https://mlsanity.com/paper/2309.17417/) (2023)
- [DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization](https://mlsanity.com/paper/2408.04400/) (2024)
- [Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks](https://mlsanity.com/paper/2404.03139/) (2024)
- [Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning](https://mlsanity.com/paper/2407.12703/) (2024)
- [Social Biases in Knowledge Representations of Wikidata separates Global North from Global South](https://mlsanity.com/paper/2505.02352/) (2025)
- [Marginal Nodes Matter: Towards Structure Fairness in Graphs](https://mlsanity.com/paper/2310.14527/) (2023)
- [Towards Better Benchmark Datasets for Inductive Knowledge Graph Completion](https://mlsanity.com/paper/2406.11898/) (2024)
- [KGMark: A Diffusion Watermark for Knowledge Graphs](https://mlsanity.com/paper/2505.23873/) (2025)
- [Role Support in Knowledge-Graph Error Ranking: Predictor Regimes and Evaluation Policies](https://mlsanity.com/paper/2512.22318/) (2025)
- [Asymmetric Learning for Graph Neural Network based Link Prediction](https://mlsanity.com/paper/2303.00170/) (2023)
- [MUSE: Integrating Multi-Knowledge for Knowledge Graph Completion](https://mlsanity.com/paper/2409.17536/) (2024)
- [DELE: Deductive EL++ Embeddings for Knowledge Base Completion](https://mlsanity.com/paper/2411.01574/) (2024)
- [Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2501.00252/) (2024)
- [Estimating Fair Graphs from Graph-Stationary Data](https://mlsanity.com/paper/2510.07536/) (2025)
- [Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation](https://mlsanity.com/paper/2608.21243/) (2026)
- [ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Prediction](https://mlsanity.com/paper/2609.36996/) (2026)

## Abstract (arXiv)

A fundamental task for knowledge graphs (KGs) is knowledge graph completion (KGC). It aims to predict unseen edges by learning representations for all the entities and relations in a KG. A common concern when learning representations on traditional graphs is degree bias. It can affect graph algorithms by learning poor representations for lower-degree nodes, often leading to low performance on such nodes. However, there has been limited research on whether there exists degree bias for embedding-based KGC and how such bias affects the performance of KGC. In this paper, we validate the existence of degree bias in embedding-based KGC and identify the key factor to degree bias. We then introduce a novel data augmentation method, KG-Mixup, to generate synthetic triples to mitigate such bias. Extensive experiments have demonstrated that our method can improve various embedding-based KGC methods and outperform other methods tackling the bias problem on multiple benchmark datasets.