Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
Abstract
We explore the relationship between neural network architectures and model accuracy under differential privacy constraints. Our findings show that architectures that perform well without differential privacy, do not necessarily do so with differential privacy. This shows that extant knowledge on neural network architecture design cannot be seamlessly translated into the differential privacy context. Moreover, as neural architecture search consumes privacy budget, future research is required to better understand the relationship between neural network architectures and model accuracy to enable better architecture design choices under differential privacy constraints.
Cite
Text
Morsbach et al. "Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design." NeurIPS 2021 Workshops: PRIML, 2021.Markdown
[Morsbach et al. "Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design." NeurIPS 2021 Workshops: PRIML, 2021.](https://mlanthology.org/neuripsw/2021/morsbach2021neuripsw-architecture/)BibTeX
@inproceedings{morsbach2021neuripsw-architecture,
title = {{Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design}},
author = {Morsbach, Felix and Dehling, Tobias and Sunyaev, Ali},
booktitle = {NeurIPS 2021 Workshops: PRIML},
year = {2021},
url = {https://mlanthology.org/neuripsw/2021/morsbach2021neuripsw-architecture/}
}