公开(公告)号：US20210209515A1

公开(公告)日：2021-07-08

申请号：US17210216

申请日：2021-03-23

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Chuanyuan Song ,  Zhi Feng ,  Liangliang Lyu

IPC: G06N20/20 ,  H04L9/00

Abstract: The present disclosure provides a joint training method and apparatus for models, a device and a storage medium. The method may include: training a first-party model to be trained using a first sample quantity of first-party training samples to obtain first-party feature gradient information; acquiring second-party feature gradient information and second sample quantity information from a second party, where the second-party feature gradient information is obtained by training, by the second party, a second-party model to be trained using a second sample quantity of second-party training samples; and determining model joint gradient information according to the first-party feature gradient information, the second-party feature gradient information, first sample quantity information and the second sample quantity information, and updating the first-party model and the second-party model according to the model joint gradient information.

公开(公告)号：US12198029B2

公开(公告)日：2025-01-14

申请号：US17210216

申请日：2021-03-23

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Chuanyuan Song ,  Zhi Feng ,  Liangliang Lyu

IPC: G06N20/20 ,  H04L9/00

Abstract: The present disclosure provides a joint training method and apparatus for models, a device and a storage medium. The method may include: training a first-party model to be trained using a first sample quantity of first-party training samples to obtain first-party feature gradient information; acquiring second-party feature gradient information and second sample quantity information from a second party, where the second-party feature gradient information is obtained by training, by the second party, a second-party model to be trained using a second sample quantity of second-party training samples; and determining model joint gradient information according to the first-party feature gradient information, the second-party feature gradient information, first sample quantity information and the second sample quantity information, and updating the first-party model and the second-party model according to the model joint gradient information.