Adversarial Learning for Debiasing Knowledge Graph Embeddings

by   Mario Arduini, et al.

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.


page 1

page 2

page 3

page 4


Measuring Social Bias in Knowledge Graph Embeddings

It has recently been shown that word embeddings encode social biases, wi...

Diversity matters: Robustness of bias measurements in Wikidata

With the widespread use of knowledge graphs (KG) in various automated AI...

Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes

Recently, link prediction algorithms based on neural embeddings have gai...

MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings

Many knowledge graph embedding methods operate on triples and are theref...

Towards Automatic Bias Detection in Knowledge Graphs

With the recent surge in social applications relying on knowledge graphs...

The KEEN Universe: An Ecosystem for Knowledge Graph Embeddings with a Focus on Reproducibility and Transferability

There is an emerging trend of embedding knowledge graphs (KGs) in contin...

Compositional Fairness Constraints for Graph Embeddings

Learning high-quality node embeddings is a key building block for machin...

Please sign up or login with your details

Forgot password? Click here to reset