# Adversarial Learning for Debiasing Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/2006.16309 · HTML: https://mlsanity.com/paper/2006.16309/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

## Built on by (most cited first, 16 of 16)

- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs](https://mlsanity.com/paper/2112.06567/) (2021)
- [Graph Learning with Localized Neighborhood Fairness](https://mlsanity.com/paper/2212.12040/) (2022)
- [Towards Automatic Bias Detection in Knowledge Graphs](https://mlsanity.com/paper/2109.10697/) (2021)
- [Mitigating Relational Bias on Knowledge Graphs](https://mlsanity.com/paper/2211.14489/) (2022)
- [The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs](https://mlsanity.com/paper/2210.03353/) (2022)
- [Social Biases in Knowledge Representations of Wikidata separates Global North from Global South](https://mlsanity.com/paper/2505.02352/) (2025)
- [Mitigating Algorithmic Bias with Limited Annotations](https://mlsanity.com/paper/2207.10018/) (2022)
- [Analyzing the Effect of Sampling in GNNs on Individual Fairness](https://mlsanity.com/paper/2209.03904/) (2022)
- [Diversity matters: Robustness of bias measurements in Wikidata](https://mlsanity.com/paper/2302.14027/) (2023)
- [Random Walks with Erasure: Diversifying Personalized Recommendations on Social and Information Networks](https://mlsanity.com/paper/2102.09635/) (2021)
- [Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation](https://mlsanity.com/paper/2308.08799/) (2023)
- [Fair Graph Machine Learning under Adversarial Missingness Processes](https://mlsanity.com/paper/2311.01591/) (2023)

## Abstract (arXiv)

Knowledge Graphs (KG) are gaining increasing attention in both academia and industry. Despite their diverse benefits, recent research have identified social and cultural biases embedded in the representations learned from KGs. Such biases can have detrimental consequences on different population and minority groups as applications of KG begin to intersect and interact with social spheres. This paper aims at identifying and mitigating such biases in Knowledge Graph (KG) embeddings. As a first step, we explore popularity bias -- the relationship between node popularity and link prediction accuracy. In case of node2vec graph embeddings, we find that prediction accuracy of the embedding is negatively correlated with the degree of the node. However, in case of knowledge-graph embeddings (KGE), we observe an opposite trend. As a second step, we explore gender bias in KGE, and a careful examination of popular KGE algorithms suggest that sensitive attribute like the gender of a person can be predicted from the embedding. This implies that such biases in popular KGs is captured by the structural properties of the embedding. As a preliminary solution to debiasing KGs, we introduce a novel framework to filter out the sensitive attribute information from the KG embeddings, which we call FAN (Filtering Adversarial Network). We also suggest the applicability of FAN for debiasing other network embeddings which could be explored in future work.