SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.12576 · 2021

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.12576")
get_code_for_paper("2106.12576")
have("2106.12576")

Connect an agent — have() is free.