Method for a distributed learning

A computer implemented method for training a learning model based on training data by means of a distributed learning system comprising computing nodes, the computing nodes respectively implementing the learning model and deriving a gradient information, Gi, corresponding to a gradient of a loss function, for updating the learning model based on the training data, the method comprising:

• encoding, by the computing nodes, the gradient information by exploiting a correlation across the gradient information from the respective computing nodes by means of an autoencoder model trained at a selected computing node by a control logic that implements a similarity loss function which estimates the similarities or the correlation across the gradient information from the respective computing nodes to extract gradient information common across the computing nodes;
• exchanging, by the computing nodes, the encoded gradient information within the distributed learning system;
• determining an aggregate gradient information, G′, based on the encoded gradient information from the computing nodes;
• and
• updating the learning model of the computing nodes with the aggregate gradient information, thereby training the learning model.