US Patent Application 18327952. MODEL TRAINING METHOD, DATA PROCESSING METHOD, AND APPARATUS simplified abstract
Contents
MODEL TRAINING METHOD, DATA PROCESSING METHOD, AND APPARATUS
Inventors
MODEL TRAINING METHOD, DATA PROCESSING METHOD, AND APPARATUS - A simplified explanation of the abstract
- This abstract for appeared for patent application number 18327952 Titled 'MODEL TRAINING METHOD, DATA PROCESSING METHOD, AND APPARATUS'
Simplified Explanation
This abstract describes a method for training a machine learning system that consists of a server and multiple client devices. The method involves the client devices receiving a shared model from the server, making predictions on a dataset using both the shared model and a private model on the client device, calculating loss values based on these predictions, and combining the loss values to update the private model.
Original Abstract Submitted
This application discloses a model training method, and relates to the field of artificial intelligence. The method provided in this application is applicable to a machine learning system. The machine learning system includes a server and at least two client side devices. The method includes: A first client side device receives a first shared model sent by the server; outputs a first prediction result for a data set through the first shared model; obtains a first loss value based on the first prediction result; outputs a second prediction result for the data set through a first private model of the first client side device; obtains a second loss value based on the second prediction result; and performs second combination processing on the first loss value and the second loss value to obtain a third loss value, where the third loss value is used to update the first private model.
