Home | Publications | RKZ+24

Complex-Valued Federated Learning With Differential Privacy and MRI Applications

MCML Authors

Link to Profile Julia Schnabel

Julia Schnabel

Prof. Dr.

Core PI

Computational Imaging and AI in Medicine

Georgios Kaissis

Georgios Kaissis

Dr.

Principal Investigator

* Former Principal Investigator

Abstract

Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many medical applications, for example magnetic resonance imaging (MRI), rely on complex-valued signal processing techniques for data acquisition and analysis. However, the appropriate application of DP to complex-valued data is still underexplored. To address this issue, from the theoretical side, we introduce the complex-valued Gaussian mechanism, whose behaviour we characterise in terms of f-DP, -DP and Rényi-DP. Moreover, we generalise the fundamental algorithm DP stochastic gradient descent to complex-valued neural networks and present novel complex-valued neural network primitives compatible with DP. Experimentally, we showcase a proof-of-concept by training federated complex-valued neural networks with DP on a real-world task (MRI pulse sequence classification in k-space), yielding excellent utility and privacy. Our results highlight the relevance of combining federated learning with robust privacy-preserving techniques in the MRI context.

inproceedings RKZ+24

DeCaF @MICCAI 2024

5th Workshop on Distributed, Collaborative and Federated Learning at the 27th International Conference on Medical Image Computing and Computer Assisted Intervention. Marrakesh, Morocco, Oct 06-10, 2024.

Authors

A. Riess • A. Ziller • S. Kolek • D. Rückert • J. A. Schnabel • G. Kaissis

Links

DOI

Research Areas

 A2 | Mathematical Foundations

 C1 | Medicine

BibTeXKey: RKZ+24

#p-kaissis #p-kutyniok #p-rueckert #p-schnabel
Back to Top