Fair Differential Privacy Can Mitigate the Disparate Impact on Model Accuracy

The techniques based on the theory of differential privacy (DP) has become a standard building block in the machine learning community. DP training mechanisms offer strong guarantees that an adversary cannot determine with high confidence about the training data based on analyzing the released model, let alone any details of the instances. However, DP may disproportionately affect the underrepresented and relatively complicated classes. That is, the reduction in utility is unequal for each class. This paper proposes a fair differential privacy algorithm (FairDP) to mitigate the disparate impact on model accuracy for each class. We cast the learning procedure as a two-stage optimization problem, which integrates differential privacy with fairness. FairDP establishes a self-adaptive DP mechanism and dynamically adjusts instance influence in each class depending on the theoretical bias-variance bound. Our experimental evaluation shows the effectiveness of FairDP in mitigating the disparate impact on model accuracy among the classes on several benchmark datasets and scenarios ranging from text to vision.