US 12,333,391 B2
Sidelink-supported federated learning for training a machine learning component
Tianyang Bai, Somerville, NJ (US); Hua Wang, Basking Ridge, NJ (US); and Junyi Li, Franklin Park, NJ (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Jan. 28, 2021, as Appl. No. 17/160,697.
Prior Publication US 2022/0237507 A1, Jul. 28, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); H04W 72/21 (2023.01); H04W 72/51 (2023.01)
CPC G06N 20/00 (2019.01) [H04W 72/21 (2023.01); H04W 72/51 (2023.01)] 30 Claims
OG exemplary drawing
 
1. A first user equipment (UE) for wireless communication, comprising:
one or more memories; and
one or more processors coupled to the one or more memories, the one or more processors configured to:
receive a request for local update assistance;
receive, from a second UE and based at least in part on the request, a sidelink communication that indicates a first subset of local training data of a set of local training data associated with the second UE; and
transmit a combined local update that is based at least in part on training a machine learning component based at least in part on the first subset of local training data and a second set of local training data associated with the first UE.