Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs

TL;DR

This paper introduces a privacy-preserving federated learning approach using a differentially private conditional VAE that produces high-quality, compact embeddings, enabling flexible, efficient, and scalable data sharing for medical imaging.

Contribution

It presents a novel DP-CVAE model that improves privacy, reduces computational costs, and supports multiple tasks, outperforming existing federated learning methods in medical imaging.

Findings

DP-CVAE produces higher-fidelity embeddings than DP-CGAN.

It requires 5 times fewer parameters than comparable models.

The method enhances privacy, scalability, and efficiency in federated data sharing.

Abstract

Deep Learning (DL) has revolutionized medical imaging, yet its adoption is constrained by data scarcity and privacy regulations, limiting access to diverse datasets. Federated Learning (FL) enables decentralized training but suffers from high communication costs and is often restricted to a single downstream task, reducing flexibility. We propose a data-sharing method via Differentially Private (DP) generative models. By adopting foundation models, we extract compact, informative embeddings, reducing redundancy and lowering computational overhead. Clients collaboratively train a Differentially Private Conditional Variational Autoencoder (DP-CVAE) to model a global, privacy-aware data distribution, supporting diverse downstream tasks. Our approach, validated across multiple feature extractors, enhances privacy, scalability, and efficiency, outperforming traditional FL classifiers while ensuring differential privacy. Additionally, DP-CVAE produces higher-fidelity embeddings than DP-CGAN while requiring $5{\times}$ fewer parameters.