Complex-valued Federated Learning with Differential Privacy and MRI Applications
This work addresses privacy concerns in medical applications like MRI by enabling federated learning with differential privacy for complex-valued data, though it is incremental as it adapts existing methods to a specific domain.
The paper tackles the underexplored application of differential privacy to complex-valued data in federated learning, introducing a complex-valued Gaussian mechanism and DP stochastic gradient descent for neural networks, and demonstrates this on MRI pulse sequence classification with excellent utility and privacy results.
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, $(\varepsilon, δ)$-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.