loading page

Differentially-private Federated Neural Architecture Search
  • +3
  • Ishika Singh ,
  • Haoyi Zhou ,
  • Kunlin Yang ,
  • Meng Ding ,
  • Bill Lin ,
  • Pengtao Xie
Ishika Singh
Author Profile
Haoyi Zhou
Author Profile
Kunlin Yang
Author Profile
Meng Ding
Author Profile
Pengtao Xie
UC San Diego

Corresponding Author:[email protected]

Author Profile

Abstract

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