Patent · US Active

Systems and methods for blind vertical learning

US11743238B2 · kind B2 · utility

1Cited by
8References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 7, 2022
Grant dateAug 29, 2023
Priority date
Expiry dateSep 7, 2042

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L2209/46
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method of providing blind vertical learning includes creating, based on assembled data, a neural network having n bottom portions and a top portion and transmitting each bottom portion of then bottom portions to a client device. The training of the neural network includes accepting a, output from each bottom portion of the neural network, joining the plurality of outputs at a fusion layer, passing the fused outputs to the top portion of the neural network, carrying out a forward propagation step at the top portion of neural network, calculating a loss value after the forward propagation step, calculating a set of gradients of the loss value with respect to server-side model parameters and passing subsets of the set of gradients to a client device. After training, the method includes combining the trained bottom portion from each client device into a combined model.

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