US Patent Issued to GOOGLE on July 21 for "Ascertaining and/or mitigating extent of effective reconstruction, of predictions, from model updates transmitted in federated learning" (California Inventors)

ALEXANDRIA, Va., July 21 -- United States Patent no. 12,688,467, issued on July 21, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Ascertaining and/or mitigating extent of effective reconstruction, of predictions, from model updates transmitted in federated learning" was invented by Om Dipakbhai Thakkar (San Jose, Calif.), Trung Dang (Los Angeles), Swaroop Indra Ramaswamy (Belmont, Calif.), Rajiv Mathews (Sunnyvale, Calif.) and Francoise Beaufays (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations relate to ascertaining to what extent predictions, generated using a machine learning model, can be effectively reconstructed from model updates, where the model updates are ...