Towards Automatic Bias Detection in Knowledge Graphs

TL;DR

This paper introduces a framework for automatically detecting biases in knowledge graph embeddings using numerical bias metrics, aiding fairer social application development.

Contribution

It presents a novel bias detection system for knowledge graphs that quantifies biases, supporting more informed debiasing decisions.

Findings

Framework successfully identifies biases in knowledge graph embeddings.

Three different bias measures demonstrated on profession prediction.

Flexible extension to additional bias types and applications.

Abstract

With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social biases, and have proposed multiple methods for debiasing them. However, in such studies, the focus has been on debiasing techniques, while the relations to be debiased are specified manually by the user. As manual specification is itself susceptible to human cognitive bias, there is a need for a system capable of quantifying and exposing biases, that can support more informed decisions on what to debias. To address this gap in the literature, we describe a framework for identifying biases present in knowledge graph embeddings, based on numerical bias metrics. We illustrate the framework with three different bias measures on the task of profession prediction, and it can be flexibly extended to further bias definitions and applications. The relations flagged as biased can then be handed to decision makers for judgement upon subsequent debiasing.