Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
FEDERATED LEARNING METHOD AND APPARATUS BASED ON SELF-ORGANIZED CLUSTER, DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/174533
Kind Code:
A1
Abstract:
The present application relates to the technical field of artificial intelligence, and discloses a federated learning (FL) method and apparatus based on a self-organized cluster, a computer device, and a computer-readable storage medium. The method comprises: acquiring a broadcast signal sent by each user equipment, and generating a corresponding cluster; determining a target user equipment in the cluster according to the cluster, and using the target user equipment as a central node; receiving model parameters sent by each user equipment, and sending the model parameters to the central node; obtaining aggregated model parameters obtained after the central node performs aggregation FL on the model parameters; and sending the aggregated model parameters to each user equipment, and updating the model parameters of a preset model in each user equipment. Thus, combined FL model training can be provided without using a pre-determined centralized cloud server, and the problem of single-point failure of a pre-determined centralized server is effectively avoided.

Inventors:
LI ZEYUAN (CN)
WANG JIANZONG (CN)
Application Number:
PCT/CN2021/097409
Publication Date:
August 25, 2022
Filing Date:
May 31, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G06K9/62; G06N20/20
Foreign References:
CN112200263A2021-01-08
CN111600707A2020-08-28
CN111212110A2020-05-29
CN112232527A2021-01-15
CN111966698A2020-11-20
US20190227980A12019-07-25
Other References:
ANONYMOUS: " Cluster Analysis (2): Graph Group Detection", 26 April 2018 (2018-04-26), XP055961182, Retrieved from the Internet [retrieved on 20220914]
Attorney, Agent or Firm:
SHENZHEN LIDAO INTELLECTUAL PROPERTY AGENCY (GENERAL PARTNERSHIP) (CN)
Download PDF: