Patent · US Active

Gradient accumulation for federated learning

US12035286B2 · kind B2 · utility

0Cited by
0References
30Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 14, 2022
Grant dateJul 9, 2024
Priority date
Expiry dateFeb 23, 2043

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04W24/02
  • WIPO fieldDigital communication
  • WIPO sectorElectrical engineering

Abstract

A UE may identify, in each round other than an initial round, a first plurality of local model update elements of a present round. The first plurality of local model update elements of the present round may be associated with an updated local machine learning model. The UE may transmit to a base station, in each round other than the initial round, over a multiple access channel via analog signaling, a second plurality of local model update elements of the present round based on a third plurality of local model update elements of the present round. The third plurality of local model update elements of the present round may correspond to a sum of the first plurality of local model update elements of the present round and a local model update error of a previous round immediately before the present round. The analog signaling may be associated with OTA aggregation.

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