Social Biases in Knowledge Representations of Wikidata separates Global North from Global South
Not on the map. Why?
Abstract (arXiv)
Knowledge Graphs have become increasingly popular due to their wide usage in various downstream applications, including information retrieval, chatbot development, language model construction, and many others. Link prediction (LP) is a crucial downstream task for knowledge graphs, as it helps to address the problem of the incompleteness of the knowledge graphs. However, previous research has shown that knowledge graphs, often created in a (semi) automatic manner, are not free from social biases. These biases can have harmful effects on downstream applications, especially by leading to unfair behavior toward minority groups. To understand this issue in detail, we develop a framework -- AuditLP -- deploying fairness metrics to identify biased outcomes in LP, specifically how occupations are classified as either male or female-dominated based on gender as a sensitive attribute. We have experimented with the sensitive attribute of age and observed that occupations are categorized as young-biased, old-biased, and age-neutral. We conduct our experiments on a large number of knowledge triples that belong to 21 different geographies extracted from the open-sourced knowledge graph, Wikidata. Our study shows that the variance in the biased outcomes across geographies neatly mirrors the socio-economic and cultural division of the world, resulting in a transparent partition of the Global North from the Global South.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 21 of its 58 references that are in the map. First posted on arXiv 5 May 2025.
Builds on
21 of 58 references.
References · 21
- 2016Complex Embeddings for Simple Link Predictioncited by 902
- 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
- 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 240
- 2015Holographic Embeddings of Knowledge Graphscited by 181
- 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
- 2018End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completioncited by 136
- 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
- 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
- 2020Knowledge Graph Embedding for Link Prediction: A Comparative Analysiscited by 85
- 2019Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modelingcited by 71
- 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
- 2019Interaction Embeddings for Prediction and Explanation in Knowledge Graphscited by 40
9 more
- 2018Hypernetwork Knowledge Graph Embeddingscited by 38
- 2015It's a Man's Wikipedia? Assessing Gender Inequality in an Online Encyclopediacited by 30
- 2019Measuring Social Bias in Knowledge Graph Embeddingscited by 17
- 2023Toward Degree Bias in Embedding-Based Knowledge Graph Completioncited by 17
- 2020Adversarial Learning for Debiasing Knowledge Graph Embeddingscited by 16
- 2021Analyzing Race and Country of Citizenship Bias in Wikidatacited by 6
- 2021Towards Automatic Bias Detection in Knowledge Graphscited by 6
- 2022The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphscited by 4
- 2023Diversity matters: Robustness of bias measurements in Wikidatacited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.