Federal learning method based on machine isomerism

Abstract

The invention discloses a federal learning method based on machine isomerism. The method comprises the following steps: receiving an initial model, a global gradient and a global model parameter which are uniformly sent by a server; obtaining an estimated gradient calibration value according to the initial model, the global gradient and the global model parameters, wherein the estimated gradient calibration value is used for representing the deviation between the local gradient of each edge device and the global gradient of the server and the deviation generated by each edge device due to different local updating times; obtaining a target local gradient and a target local model parameter based on the estimated gradient calibration value; and sending the target local gradient and the target local model parameter to the server, so that the server generates an updated global gradient and an updated global model parameter. According to the embodiment of the invention, the deviation between each edge device and the server is removed through the estimated gradient calibration technology of each edge device, and the deviation caused by different local updating times is compensated, so that the training efficiency of federal learning is improved. 本发明公开了一种基于机器异构性的联邦学习方法，方法包括：接收服务器统一发送的初始模型、全局梯度和全局模型参数；根据初始模型、全局梯度和全局模型参数，得到预估梯度校准值；其中，预估梯度校准值用于表征各边缘设备的本地梯度与服务器的全局梯度的偏差以及各边缘设备因本地更新次数不同而产生的偏差；基于预估梯度校准值，得到目标本地梯度和目标本地模型参数；将所述目标本地梯度和所述目标本地模型参数发送至所述服务器，以使所述服务器生成更新后的全局梯度和全局模型参数。本发明实施例通过对各边缘设备的预估梯度校准技术来实现移除各边缘设备与服务器的偏差，同时补偿本地更新次数不同导致的偏差，从而提高联邦学习的训练效率。