TechRxiv
federated_nas_arxiv (7).pdf (321.79 kB)

Differentially-private Federated Neural Architecture Search

Download (321.79 kB)
preprint
posted on 19.06.2020, 11:10 by Ishika Singh, Haoyi Zhou, Kunlin Yang, Meng Ding, Bill Lin, Pengtao Xie
Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In many application scenarios, several parties would like to collaboratively search for a shared neural architecture by leveraging data from all parties. However, due to privacy concerns, no party wants its data to be seen by other parties. To address this problem, we propose federated neural architecture search (FNAS), where different parties collectively search for a differentiable architecture by exchanging gradients of architecture variables without exposing their data to other parties. To further preserve privacy, we study differentially-private FNAS (DP-FNAS), which adds random noise to the gradients of architecture variables. We provide theoretical guarantees of DP-FNAS in achieving differential privacy. Experiments show that DP-FNAS can search highly-performant neural architectures while protecting the privacy of individual parties. The code is available at https://github.com/UCSD-AI4H/DP-FNAS

History

Email Address of Submitting Author

pengtaoxie2008@gmail.com

Submitting Author's Institution

UC San Diego

Submitting Author's Country

United States of America

Licence

Exports

Licence

Exports