Heterogeneous client-oriented joint learning method based on stratified sampling optimization

The invention discloses a stratified sampling optimization-based joint learning method for heterogeneous clients. The method comprises the following steps of: selecting available clients from different clusters; the parameter server broadcasts the global model to all clients, the clients train samples of local data to obtain local model parameters, the parameter server collects local model parameter information of each client, and the clients are divided into different clusters by adopting a clustering method; during each round of training, available clients are extracted from each cluster according to sample weights to participate in training, and gradient aggregation is carried out; and after receiving the latest global model parameters from the parameter server in each round, the client participating in training calculates the gradient under the current parameters by using local data, the latest parameters are sent back to the parameter server after iteration, and the parameter server performs weighted ave