# Measuring Social Bias in Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/1912.02761 · HTML: https://mlsanity.com/paper/1912.02761/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

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

- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding](https://mlsanity.com/paper/2110.03789/) (2021)
- [Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis](https://mlsanity.com/paper/2104.04676/) (2021)
- [KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding](https://mlsanity.com/paper/2210.04105/) (2022)
- [Analyzing Race and Country of Citizenship Bias in Wikidata](https://mlsanity.com/paper/2108.05412/) (2021)
- [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)
- [Erasure of Unaligned Attributes from Neural Representations](https://mlsanity.com/paper/2302.02997/) (2023)
- [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)
- [Diversity matters: Robustness of bias measurements in Wikidata](https://mlsanity.com/paper/2302.14027/) (2023)
- [How Contentious Terms About People and Cultures are Used in Linked Open Data](https://mlsanity.com/paper/2311.10757/) (2023)
- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)
- [Network Report: A Structured Description for Network Datasets](https://mlsanity.com/paper/2206.03635/) (2022)
- [Mining Path Association Rules in Large Property Graphs (with Appendix)](https://mlsanity.com/paper/2408.02029/) (2024)

## Abstract (arXiv)

It has recently been shown that word embeddings encode social biases, with a harmful impact on downstream tasks. However, to this point there has been no similar work done in the field of graph embeddings. We present the first study on social bias in knowledge graph embeddings, and propose a new metric suitable for measuring such bias. We conduct experiments on Wikidata and Freebase, and show that, as with word embeddings, harmful social biases related to professions are encoded in the embeddings with respect to gender, religion, ethnicity and nationality. For example, graph embeddings encode the information that men are more likely to be bankers, and women more likely to be homekeepers. As graph embeddings become increasingly utilized, we suggest that it is important the existence of such biases are understood and steps taken to mitigate their impact.