Decentralized Federated Learning through Proxy Model Sharing

Abstract

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.

References in corpus (4)

• Decentralized Federated Learning through Proxy Model Sharing
• Bayesian Nonparametric Federated Learning of Neural Networks
• Decentralized Federated Learning via Mutual Knowledge Transfer
• FLOP: Federated Learning on Medical Datasets using Partial Networks

Cited by in corpus (10)

• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection
• Decentralized Federated Learning through Proxy Model Sharing
• Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations
• Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI
• Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges
• Collaborative Distributed Machine Learning
• Decentralized Personalization for Federated Medical Image Segmentation via Gossip Contrastive Mutual Learning
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator