公开(公告)号：US20230237333A1

公开(公告)日：2023-07-27

申请号：US18185550

申请日：2023-03-17

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yunfeng SHAO ,  Shaoming SONG ,  Wenpeng LI ,  Kaiyang GUO ,  Li QIAN

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A machine learning model training method is applied to a first client, a plurality of clients are communicatively connected to a server, the server stores a plurality of modules, and the plurality of modules are configured to construct at least two machine learning models. The method includes: obtaining a first machine learning model, where at least one first machine learning model is selected based on a data feature of a first training data set stored in the first client; performing a training operation on the at least one first machine learning model by using the first data set, to obtain at least one trained first machine learning model; and sending at least one updated module to the server, where the updated module is used by the server to update weight parameters of the stored modules.

公开(公告)号：US20230325722A1

公开(公告)日：2023-10-12

申请号：US18327952

申请日：2023-06-02

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： De-Chuan ZHAN ,  Xinchun LI ,  Shaoming SONG ,  Yunfeng SHAO ,  Bingshuai LI ,  Li QIAN

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: 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.