US 11,681,951 B2
Semantic learning in a federated learning system
Vito Paolo Pastore, Lecce (IT); Yi Zhou, San Jose, CA (US); Nathalie Baracaldo Angel, San Jose, CA (US); Ali Anwar, San Jose, CA (US); and Simone Bianco, San Francisco, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Aug. 8, 2022, as Appl. No. 17/818,132.
Application 17/818,132 is a continuation of application No. 17/022,140, filed on Sep. 16, 2020, granted, now 11,494,700.
Prior Publication US 2022/0383132 A1, Dec. 1, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 29/08 (2006.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); H04L 67/10 (2022.01); G06N 3/04 (2023.01); G06N 3/088 (2023.01); G06N 3/045 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 40/30 (2020.01); G06N 3/04 (2013.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01); H04L 67/10 (2013.01)] 20 Claims
OG exemplary drawing
 
14. A computer system for federated learning enhanced with semantic learning, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
receiving cluster information from distributed computing devices, wherein the cluster information relates to identified clusters in sample data of the distributed computing devices and comprises centroid information per cluster;
integrating the cluster information to define data classes for machine learning classification, wherein the integrating comprises computing a respective distance between centroids of the clusters in order to determine a total number of the data classes; and
sending a deep learning model comprising an output layer comprising a total number of nodes equal to the total number of the data classes, and wherein the deep learning model is for the distributed computing devices to perform machine learning classification in federated learning.