Joint model training method, system and device and computer readable storage medium

Abstract

The invention discloses a federal model training method, a federal model training system, federal model training equipment and a computer readable storage medium, and the method comprises the steps: obtaining a weight coefficient corresponding to each model parameter according to a preset obtaining rule after a cooperative terminal receives the model parameters respectively sent by a plurality ofclient terminals; according to the plurality of model parameters and the weight coefficient corresponding to each model parameter, aggregating to obtain a second global model; detecting whether the second global model converges or not; and if it is detected that the second global model is in the convergence state, determining the second global model as a final result of federated model training, and issuing the second global model with encrypted parameters to a plurality of client terminals. According to the invention, the cooperative terminal updates and obtains the new global model accordingto the model parameter and the weight coefficient of each client terminal, and the prediction effect of the federal model is improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a federated model training method, system, device and computer-readable storage medium. Background technique [0002] The federated model is a machine learning model built using technical algorithm encryption. Multiple federated clients in the federated learning system do not need to give their own data during model training, but the global model encrypted according to the parameters issued by the collaborative end and the client's local data. The data set is used to train the local model, and the parameters of the local model are returned for the collaboration end to aggregate and update the global model. The updated global model is re-delivered to the client, and the cycle repeats until convergence. Federated learning protects client data privacy by exchanging parameters under an encryption mechanism. Client data and the client’s local model itself will not be ...

Images