The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Aug. 06, 2024

Filed:

Jul. 06, 2020
Applicant:

Beijing Baidu Netcom Science and Technology Co., Ltd., Beijing, CN;

Inventors:

Bing Ren, Beijing, CN;

Shengwen Yang, Beijing, CN;

Xuhui Zhou, Beijing, CN;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 21/60 (2013.01); H04L 9/00 (2022.01); H04L 9/08 (2006.01); H04L 9/30 (2006.01);
U.S. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 21/602 (2013.01); H04L 9/008 (2013.01); H04L 9/0825 (2013.01); H04L 9/3073 (2013.01); G06F 2221/2107 (2013.01);
Abstract

A method and device for training a model based on federated learning are provided. The method includes: receiving a second original independent variable calculated value from a second data provider device; the second original independent variable calculated value being calculated by the second data provider device according to a second original independent variable and a second model parameter; calculating a dependent variable estimation value according to a first model parameter initial value of a first provider device, a first original independent variable of the first data provider device, and the second original independent variable calculated value; calculating a difference between a dependent variable of the first data provider device and the dependent variable estimation value; calculating a gradient of a loss function with respect to a first model parameter, according to the difference; and updating the first model parameter according to the gradient of the loss function with respect to the first model parameter.


Find Patent Forward Citations

Loading…