A Fairness Analysis on Private Aggregation of Teacher Ensembles
It addresses fairness issues in privacy-preserving machine learning, which is crucial for ensuring equitable outcomes in sensitive applications, though it is incremental as it builds on existing PATE methods.
This paper investigates whether the Private Aggregation of Teacher Ensembles (PATE) framework introduces or worsens bias and unfairness, finding that it can cause accuracy disparities among individuals and groups, and proposes guidelines to mitigate these effects.
The Private Aggregation of Teacher Ensembles (PATE) is an important private machine learning framework. It combines multiple learning models used as teachers for a student model that learns to predict an output chosen by noisy voting among the teachers. The resulting model satisfies differential privacy and has been shown effective in learning high-quality private models in semisupervised settings or when one wishes to protect the data labels. This paper asks whether this privacy-preserving framework introduces or exacerbates bias and unfairness and shows that PATE can introduce accuracy disparity among individuals and groups of individuals. The paper analyzes which algorithmic and data properties are responsible for the disproportionate impacts, why these aspects are affecting different groups disproportionately, and proposes guidelines to mitigate these effects. The proposed approach is evaluated on several datasets and settings.