Towards Reducing Bias in Gender Classification
This addresses bias in gender recognition systems, which can harm marginalized communities, but it is incremental as it builds on existing adversarial methods.
The paper tackled racial bias in gender classification systems by learning race-invariant face representations using an adversarially trained autoencoder, resulting in a drop of over 40% in variance in classification accuracy across races.
Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant representations of human faces with an adversarially trained autoencoder model. We show that such representations help us achieve less biased performance in gender classification. We use variance in classification accuracy across different races as a surrogate for the racial bias of the model and achieve a drop of over 40% in variance with race invariant representations.