查看文章

A federated learning method using data digest includes: sending a general model to multiple client devices by a moderator, generating encoded features according to raw data and performing a training procedure by each client device, wherein the training procedure includes “updating the general model to generate a client model, selecting at least two encoded features and at least two labels to compute a feature weighted sum and a label weighted sum, sending the feature weighted sum and the label weighted sum as a digest to the moderator and send update parameters of the client model”, and “determining an absent client and an present client among the client devices, generating a replacement model according to the general model and the absent client, generating an aggregation model according to the present client and the replacement model, and training the aggregation model to update the general …