在神经形态硬件上实现联邦少样本学习，验证了新策略的高精度与机制原理。
Federated Few-Shot Learning on Neuromorphic Hardware: An Empirical Study Across Physical Edge Nodes
- 采用神经元级权重拼接策略，克服二值化更新对精度的破坏
- 特征维度从64提升至256，联邦准确率达77.0%（p<0.001）
- 适合边缘计算、低功耗场景下的分布式小样本学习研究者
在神经形态硬件上的联邦学习尚未被探索，因为片上脉冲时序依赖可塑性（STDP）产生二值权重更新，而非标准算法假设的浮点梯度。我们构建了一个由两个节点组成的联邦系统，使用BrainChip Akida AKD1000处理器，共执行约1,580次实验，涵盖七个分析阶段。在测试的四种权重交换策略中，神经元级拼接（FedUnion）始终维持精度，而元素级平均（FedAvg）则显著损害精度（p = 0.002）。上游特征提取器的域自适应微调贡献了主要的精度提升，证实特征质量是决定性因素。将特征维度从64扩大到256，使最佳策略的联邦准确率达到77.0%（n=30，p < 0.001）。两种独立不对称性（更宽特征对联邦更有利，而二值化对联邦伤害更大）指向一个共享原型互补机制：跨节点迁移效果随神经元原型差异性增强而提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。