FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes

Understand

Most fair machine learning methods either highly rely on the sensitive information of the training samples or require a large modification on the target models, which hinders their practical application.

• To address this issue, we propose a two-stage training algorithm named FAIRIF.
• It minimizes the loss over the reweighted data set (second stage) where the sample weights are computed to balance the model performance across different demographic groups (first stage).
• FAIRIF can be applied on a wide range of models trained by stochastic gradient descent without changing the model, while only requiring group annotations on a small validation set to compute sample weights.