Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Machine Learning for Data: Automated Creation, Privacy, Bias

DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?

Archit Uniyal · Rakshit Naidu · Sasikanth Kotti · Patrik Joslin Kenfack · Sahib Singh · FatemehSadat Mireshghallah


Abstract:

Recent advances in differentially private deep learning have demonstrated that application of differential privacy-- specifically the DP-SGD algorithm-- has a disparate impact on different sub-groups in the population, which leads to a significantly high drop-in model utility for sub-populations that are under-represented (minorities), compared to well-represented ones. In this work, we aim to compare PATE, another mechanism for training deep learning models using differential privacy, with DP-SGD in terms of fairness. We show that PATE does have a disparate impact too, however, it is much less severe than DP-SGD. We draw insights from this observation on what might be promising directions in achieving better fairness-privacy trade-offs.

Chat is not available.