Identifying and mitigating disparate group impact in differential-privacy machine-learned models

Abstract

A model evaluation system evaluates the extent to which privacy-aware training processes affect the direction of training gradients for groups. A modified differential-privacy ('DP') training process provides per-sample gradient adjustments with parameters that may be adaptively modified for different data batches. Per-sample gradients are modified with respect to a reference bound and a clipping bound. A scaling factor may be determined for each per-sample gradient based on the higher of the reference bound or a magnitude of the per-sample gradient. Per-sample gradients may then be adjusted based on a ratio of the clipping bound to the scaling factor. A relative privacy cost between groups may be determined as excess training risk based on a difference in group gradient direction relative to an unadjusted batch gradient and the adjusted batch gradient according to the privacy-aware training.