Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning strategy, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection mechanism, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices on the fly based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 16.83% inference improvements for both IID and non-IID scenarios.

翻译：尽管联邦学习（FL）有望实现人工智能物联网（AIoT）设备的协同学习，但由于设备存在多种异质性因素（如计算能力、内存大小）以及不确定的运行环境，其面临分类性能低下等问题。为解决这些问题，本文提出了一种基于新颖的细粒度宽度级模型剪枝策略的高效FL方法——AdaptiveFL，该方法可为异构AIoT设备生成多样化的异构局部模型。通过采用本文提出的基于强化学习的设备选择机制，AdaptiveFL能够根据AIoT设备的可用资源，实时自适应地为其分配合适的异构模型进行本地训练。实验结果表明，与现有最优方法相比，AdaptiveFL在独立同分布（IID）与非独立同分布（non-IID）场景下均可实现高达16.83%的推理性能提升。