Federated Learning in Open- and Closed-Loop EMG Decoding: A Privacy and Performance Perspective
This work addresses privacy challenges in neural interfaces for users with sensitive health data, but it is incremental as it adapts existing FL methods to a new application without major breakthroughs.
The study tackled the problem of privacy risks in neural signal data sharing for decoder training by applying federated learning (FL) to electromyography decoding in open- and closed-loop scenarios. In open-loop simulations, FL outperformed local learning baselines, but in closed-loop user studies, adapted FL methods were surpassed by local learning in performance while still offering lower privacy risks.
Invasive and non-invasive neural interfaces hold promise as high-bandwidth input devices for next-generation technologies. However, neural signals inherently encode sensitive information about an individual's identity and health, making data sharing for decoder training a critical privacy challenge. Federated learning (FL), a distributed, privacy-preserving learning framework, presents a promising solution, but it remains unexplored in closed-loop adaptive neural interfaces. Here, we introduce FL-based neural decoding and systematically evaluate its performance and privacy using high-dimensional electromyography signals in both open- and closed-loop scenarios. In open-loop simulations, FL significantly outperformed local learning baselines, demonstrating its potential for high-performance, privacy-conscious neural decoding. In contrast, closed-loop user studies required adapting FL methods to accommodate single-user, real-time interactions, a scenario not supported by standard FL. This modification resulted in local learning decoders surpassing the adapted FL approach in closed-loop performance, yet local learning still carried higher privacy risks. Our findings highlight a critical performance-privacy tradeoff in real-time adaptive applications and indicate the need for FL methods specifically designed for co-adaptive, single-user applications.