论文标题
差异私有联盟的神经建筑搜索
Differentially-private Federated Neural Architecture Search
论文作者
论文摘要
神经体系结构搜索旨在自动搜索最大化验证性能的神经网络的架构（例如，卷积，最大池化），最近取得了显着的进步。在许多应用程序方案中，多方希望通过利用各方的数据来协作搜索共享的神经体系结构。但是，由于隐私问题，没有一方希望其他方看到其数据。为了解决这个问题，我们提出了联合的神经体系结构搜索（FNA），在那里不同的各方通过交换架构变量的梯度而不将其数据公开给其他各方，共同搜索了可区分的体系结构。为了进一步保留隐私，我们研究了差异私有的FNA（DP-FNA），从而为建筑变量的梯度增加了随机噪声。我们提供了DP-FNA在实现差异隐私方面的理论保证。实验表明，DP-FNA可以在保护各方隐私的同时搜索高性能的神经体系结构。该代码可从https://github.com/ucsd-ai4h/dp-fnas获得
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
