Layer 6 AI, Toronto, ON, Canada.
Kimia Lab, University of Waterloo, Toronto, ON, Canada.
Nat Commun. 2023 May 22;14(1):2899. doi: 10.1038/s41467-023-38569-4.
Institutions in highly regulated domains such as finance and healthcare often have restrictive rules around data sharing. Federated learning is a distributed learning framework that enables multi-institutional collaborations on decentralized data with improved protection for each collaborator's data privacy. In this paper, we propose a communication-efficient scheme for decentralized federated learning called ProxyFL, or proxy-based federated learning. Each participant in ProxyFL maintains two models, a private model, and a publicly shared proxy model designed to protect the participant's privacy. Proxy models allow efficient information exchange among participants without the need of a centralized server. The proposed method eliminates a significant limitation of canonical federated learning by allowing model heterogeneity; each participant can have a private model with any architecture. Furthermore, our protocol for communication by proxy leads to stronger privacy guarantees using differential privacy analysis. Experiments on popular image datasets, and a cancer diagnostic problem using high-quality gigapixel histology whole slide images, show that ProxyFL can outperform existing alternatives with much less communication overhead and stronger privacy.
在金融和医疗等高度监管领域的机构通常对数据共享有严格的规定。联邦学习是一种分布式学习框架，它可以在去中心化的数据上实现多机构合作，同时提高每个合作者数据隐私的保护。在本文中，我们提出了一种称为 ProxyFL（代理联邦学习）的高效通信去中心化联邦学习方案。ProxyFL 中的每个参与者维护两个模型，一个私有模型和一个公共共享的代理模型，旨在保护参与者的隐私。代理模型允许参与者之间进行有效的信息交换，而无需中央服务器。所提出的方法通过允许模型异构性消除了经典联邦学习的一个显著限制；每个参与者都可以拥有具有任何架构的私有模型。此外，我们的代理通信协议通过差分隐私分析提供了更强的隐私保证。在流行的图像数据集和使用高质量千兆像素组织学全切片图像的癌症诊断问题上的实验表明，ProxyFL 可以在更少的通信开销和更强的隐私性方面胜过现有替代方案。
