Federated Few-Shot Learning on Neuromorphic Hardware: An Empirical Study Across Physical Edge Nodes
This addresses the problem of enabling federated learning on neuromorphic hardware for edge computing applications, but it is incremental as it builds on existing methods with empirical validation.
The study tackled federated learning on neuromorphic hardware by testing weight-exchange strategies, finding that neuron-level concatenation preserved accuracy while averaging destroyed it, with scaling feature dimensionality to 256 achieving 77.0% federated accuracy.
Federated learning on neuromorphic hardware remains unexplored because on-chip spike-timing-dependent plasticity (STDP) produces binary weight updates rather than the floating-point gradients assumed by standard algorithms. We build a two-node federated system with BrainChip Akida AKD1000 processors and run approximately 1,580 experimental trials across seven analysis phases. Of four weight-exchange strategies tested, neuron-level concatenation (FedUnion) consistently preserves accuracy while element-wise weight averaging (FedAvg) destroys it (p = 0.002). Domain-adaptive fine-tuning of the upstream feature extractor accounts for most of the accuracy gains, confirming feature quality as the dominant factor. Scaling feature dimensionality from 64 to 256 yields 77.0% best-strategy federated accuracy (n=30, p < 0.001). Two independent asymmetries (wider features help federation more than individual learning, while binarization hurts federation more) point to a shared prototype complementarity mechanism: cross-node transfer scales with the distinctiveness of neuron prototypes.