On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms
This addresses privacy-preserving, efficient learning for intelligent nano-drone swarms, representing an incremental advance in domain-specific optimization.
The paper tackles the challenge of on-device federated continual learning for battery-operated nano-drones by proposing a regularization-based algorithm, improving classification accuracy by 24% over naive fine-tuning with local epochs of 178 ms and global epochs of 10.5 s on a RISC-V-based SoC.
RISC-V-based architectures are paving the way for efficient On-Device Learning (ODL) in smart edge devices. When applied across multiple nodes, ODL enables the creation of intelligent sensor networks that preserve data privacy. However, developing ODL-capable, battery-operated embedded platforms presents significant challenges due to constrained computational resources and limited device lifetime, besides intrinsic learning issues such as catastrophic forgetting. We face these challenges by proposing a regularization-based On-Device Federated Continual Learning algorithm tailored for multiple nano-drones performing face recognition tasks. We demonstrate our approach on a RISC-V-based 10-core ultra-low-power SoC, optimizing the ODL computational requirements. We improve the classification accuracy by 24% over naive fine-tuning, requiring 178 ms per local epoch and 10.5 s per global epoch, demonstrating the effectiveness of the architecture for this task.