Mitigating Algorithmic Bias on Facial Expression Recognition

TL;DR

This paper addresses the challenge of biased datasets in facial expression recognition by proposing a debiasing variational autoencoder to promote fairer treatment of minority groups.

Contribution

It introduces a novel debiasing autoencoder approach specifically designed to mitigate dataset bias in facial expression recognition tasks.

Findings

Reduced bias in facial expression classification results

Improved fairness across minority and majority groups

Demonstrated effectiveness on real-world datasets

Abstract

Biased datasets are ubiquitous and present a challenge for machine learning. For a number of categories on a dataset that are equally important but some are sparse and others are common, the learning algorithms will favor the ones with more presence. The problem of biased datasets is especially sensitive when dealing with minority people groups. How can we, from biased data, generate algorithms that treat every person equally? This work explores one way to mitigate bias using a debiasing variational autoencoder with experiments on facial expression recognition.