US 12,307,364 B2
Federated learning with varying feedback
Mahmoud Taherzadeh Boroujeni, San Diego, CA (US); Tao Luo, San Diego, CA (US); Hamed Pezeshki, San Diego, CA (US); Vinay Chande, San Diego, CA (US); and Taesang Yoo, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Sep. 20, 2021, as Appl. No. 17/479,916.
Claims priority of provisional application 63/083,719, filed on Sep. 25, 2020.
Claims priority of provisional application 63/083,728, filed on Sep. 25, 2020.
Claims priority of provisional application 63/083,756, filed on Sep. 25, 2020.
Prior Publication US 2022/0101131 A1, Mar. 31, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 17/18 (2006.01); G06N 3/042 (2023.01); G06N 3/084 (2023.01)
CPC G06N 3/08 (2013.01) [G06F 17/18 (2013.01); G06N 3/042 (2023.01); G06N 3/084 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A method of wireless communication, by a user equipment (UE), comprising:
receiving, from a base station, a jointly trained artificial neural network;
calculating a value representing at least one of (1) a gradient estimate for a weight of the jointly trained artificial neural network, or (2) the weight of the jointly trained artificial neural network;
expanding the value into a numerical system with base N into a plurality of digits;
determining a number of digits and/or digit locations of the plurality of digits to transmit based on a deterministic task assignment rule received from the base station or a probabilistic task assignment rule;
transmitting the determined number of digits and/or the determined digit locations of the plurality of digits to the base station; and
operating, by the UE, according to an artificial neural network trained by the base station based on the plurality of digits transmitted to the base station.