The field of Tiny Machine Learning (TinyML) has made substantial advancements in democratizing machine learning on low-footprint devices, such as microcontrollers. The prevalence of these miniature devices raises the question of whether aggregating their knowledge can benefit TinyML applications. Federated meta-learning is a promising answer to this question, as it addresses the scarcity of labeled data and heterogeneous data distribution across devices in the real world. However, deploying TinyML hardware faces unique resource constraints, making existing methods impractical due to energy, privacy, and communication limitations. We introduce TinyMetaFed, a model-agnostic meta-learning framework suitable for TinyML. TinyMetaFed facilitates collaborative training of a neural network initialization that can be quickly fine-tuned on new devices. It offers communication savings and privacy protection through partial local reconstruction and Top-P% selective communication, computational efficiency via online learning, and robustness to client heterogeneity through few-shot learning. The evaluations on three TinyML use cases demonstrate that TinyMetaFed can significantly reduce energy consumption and communication overhead, accelerate convergence, and stabilize the training process.

翻译：微型机器学习（TinyML）领域在推动微控制器等低功耗设备上机器学习民主化方面取得了显著进展。这些微型设备的普及引发了新问题：聚合其知识能否惠及TinyML应用？联邦元学习为此提供了极具前景的解决方案，它能有效应对现实场景中标注数据稀缺及跨设备数据异构分布的挑战。然而，部署TinyML硬件面临着独特的资源约束，现有方法因受限于能耗、隐私和通信瓶颈而难以实际应用。我们提出TinyMetaFed——一种适用于TinyML的模型无关元学习框架。该框架通过协同训练神经网络初始参数，可在新设备上实现快速微调。其采用局部部分重建与Top-P%选择性通信策略以节省通信开销并保护隐私，通过在线学习提升计算效率，并借助小样本学习增强对客户异构性的鲁棒性。在三个TinyML用例上的评估表明，TinyMetaFed能显著降低能耗与通信开销，加速收敛并稳定训练过程。