Fair Generative Modeling via Weak Supervision

Understand

Real-world datasets are often biased with respect to key demographic factors such as race and gender.

• Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine learning.
• We present a weakly supervised algorithm for overcoming dataset bias for deep generative models.
• Our approach requires access to an additional small, unlabeled reference dataset as the supervision signal, thus sidestepping the need for explicit labels on the underlying bias factors.