Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition

TL;DR

This paper reviews and classifies metrics for measuring demographic bias in datasets, applies them to facial expression recognition datasets, and identifies a minimal set of effective metrics for bias assessment.

Contribution

It introduces a taxonomy for bias metrics, provides a practical guide for their selection, and demonstrates their application through a case study on FER datasets.

Findings

Many metrics are redundant in bias measurement.

A reduced subset of metrics can effectively measure demographic bias.

Insights help improve fairness in AI models.

Abstract

Demographic biases in source datasets have been shown as one of the causes of unfairness and discrimination in the predictions of Machine Learning models. One of the most prominent types of demographic bias are statistical imbalances in the representation of demographic groups in the datasets. In this paper, we study the measurement of these biases by reviewing the existing metrics, including those that can be borrowed from other disciplines. We develop a taxonomy for the classification of these metrics, providing a practical guide for the selection of appropriate metrics. To illustrate the utility of our framework, and to further understand the practical characteristics of the metrics, we conduct a case study of 20 datasets used in Facial Emotion Recognition (FER), analyzing the biases present in them. Our experimental results show that many metrics are redundant and that a reduced subset of metrics may be sufficient to measure the amount of demographic bias. The paper provides valuable insights for researchers in AI and related fields to mitigate dataset bias and improve the fairness and accuracy of AI models. The code is available at https://github.com/irisdominguez/dataset_bias_metrics.