DeepAI AI Chat
Log In Sign Up

Differentially-private Federated Neural Architecture Search

by   Ishika Singh, et al.

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


page 1

page 2

page 3

page 4


DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy

Training deep neural networks (DNNs) for meaningful differential privacy...

Dopamine: Differentially Private Federated Learning on Medical Data

While rich medical datasets are hosted in hospitals distributed across t...

On the Importance of Architecture and Feature Selection in Differentially Private Machine Learning

We study a pitfall in the typical workflow for differentially private ma...

From Federated Learning to Federated Neural Architecture Search: A Survey

Federated learning is a recently proposed distributed machine learning p...

Differentially Private Federated Clustering over Non-IID Data

Federated clustering (FedC) is an adaptation of centralized clustering i...

Neural Architecture Search for Visual Anomaly Segmentation

This paper presents AutoPatch, the first application of neural architect...

Content-Aware Differential Privacy with Conditional Invertible Neural Networks

Differential privacy (DP) has arisen as the gold standard in protecting ...