Patent · US Active

Method and device for training a model based on federated learning

US12056582B2 · kind B2 · utility

0Cited by
0References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 6, 2020
Grant dateAug 6, 2024
Priority date
Expiry dateMay 29, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2221/2107
  • WIPO fieldDigital communication
  • WIPO sectorElectrical engineering

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.