Personalized Federated Learning (PFL) is widely employed in IoT applications to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying degrees of resource constraints, causing computation and communication bottlenecks for PFL. Federated Dropout has emerged as a popular strategy to address this challenge, wherein only a subset of the global model, i.e. a \textit{sub-model}, is trained on a client's device, thereby reducing computation and communication overheads. Nevertheless, the dropout-based model-pruning strategy may introduce bias, particularly towards non-iid local data. When biased sub-models absorb highly divergent parameters from other clients, performance degradation becomes inevitable. In response, we propose federated learning with stochastic parameter update (FedSPU). Unlike dropout that tailors the global model to small-size local sub-models, FedSPU maintains the full model architecture on each device but randomly freezes a certain percentage of neurons in the local model during training while updating the remaining neurons. This approach ensures that a portion of the local model remains personalized, thereby enhancing the model's robustness against biased parameters from other clients. Experimental results demonstrate that FedSPU outperforms federated dropout by 7.57\% on average in terms of accuracy. Furthermore, an introduced early stopping scheme leads to a significant reduction of the training time by \(24.8\%\sim70.4\%\) while maintaining high accuracy.

翻译：个性化联邦学习广泛应用于物联网场景，以处理海量非独立同分布的客户端数据并保障数据隐私。然而，客户端拥有的异构边缘设备可能带来不同程度的资源约束，导致计算和通信瓶颈。联邦丢弃策略成为应对该挑战的常用方法，即客户端设备仅训练全局模型的子集（即子模型）以降低计算和通信开销。但基于丢弃的模型剪枝策略可能引入偏差，尤其针对非独立同分布的本地数据。当带有偏差的子模型从其他客户端吸收高度差异化的参数时，性能退化将不可避免。为此，我们提出基于随机参数更新的联邦学习（FedSPU）。与丢弃策略将全局模型裁剪为小型本地子模型不同，FedSPU在每台设备上保持完整模型架构，但训练期间随机冻结本地模型中一定比例的神经元并更新其余神经元。该方法确保本地模型部分参数保持个性化，从而增强模型对来自其他客户端的有偏参数的鲁棒性。实验结果表明，FedSPU的准确率平均比联邦丢弃提升7.57%。此外，引入的早停机制能在保持高准确率的同时，将训练时间显著降低24.8%至70.4%。