Federated learning is a machine learning approach in which data is not aggregated on a server, but is trained at clients locally, in consideration of security and privacy. ResNet is a classic but representative neural network that succeeds in deepening the neural network by learning a residual function that adds the inputs and outputs together. In federated learning, communication is performed between the server and clients to exchange weight parameters. Since ResNet has deep layers and a large number of parameters, the communication size becomes large. In this paper, we use Neural ODE as a lightweight model of ResNet to reduce communication size in federated learning. In addition, we newly introduce a flexible federated learning using Neural ODE models with different number of iterations, which correspond to ResNet models with different depths. Evaluation results using CIFAR-10 dataset show that the use of Neural ODE reduces communication size by up to 92.4% compared to ResNet. We also show that the proposed flexible federated learning can merge models with different iteration counts or depths.

翻译：联邦学习是一种机器学习方法，其数据不汇总于服务器，而是在客户端本地进行训练，以兼顾安全性与隐私保护。ResNet作为经典且具代表性的神经网络，通过残差函数学习将输入与输出相加，成功实现了网络深度的扩展。在联邦学习中，服务器与客户端需通过通信交换权重参数。由于ResNet层数深且参数规模庞大，导致通信开销显著增大。本文采用神经常微分方程（Neural ODE）作为ResNet的轻量化模型，以缩减联邦学习中的通信规模。此外，我们创新性地引入了一种基于不同迭代次数的Neural ODE模型的灵活联邦学习框架，该框架可对应不同深度的ResNet模型。基于CIFAR-10数据集的评估结果表明，与ResNet相比，采用Neural ODE的模型通信规模最多可减少92.4%。同时，我们验证了所提灵活联邦学习方法能够融合具有不同迭代次数或深度的模型。