Invention Application
- Patent Title: FEDERATED LEARNING METHOD, COMPUTING DEVICE AND STORAGE MEDIUM
-
Application No.: US17864098Application Date: 2022-07-13
-
Publication No.: US20220366320A1Publication Date: 2022-11-17
- Inventor: Ji LIU , Chendi ZHOU , Juncheng JIA , Dejing DOU
- Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
- Applicant Address: CN Beijing
- Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
- Current Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
- Current Assignee Address: CN Beijing
- Priority: CN202110792130.3 20210713
- Main IPC: G06N20/20
- IPC: G06N20/20

Abstract:
A computer-implemented method is provided. The method includes: executing, for each task in a federated learning system, a first training process comprising: obtaining resource information of a plurality of terminal devices of the federated learning system; determining one or more target terminal devices corresponding to the task based on the resource information; and training a global model corresponding to the task by the target terminal devices until the global model meets a preset condition.
Information query