Invention Grant
- Patent Title: Group-common reference signal for over-the-air aggregation in federated learning
-
Application No.: US17898180Application Date: 2022-08-29
-
Publication No.: US12261792B2Publication Date: 2025-03-25
- Inventor: Hamed Pezeshki , Tao Luo , Taesang Yoo , Mahmoud Taherzadeh Boroujeni , Eren Balevi , Srinivas Yerramalli , Junyi Li
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Agency: Procopio, Cory, Hargreaves & Savitch LLP
- Main IPC: H04L5/00
- IPC: H04L5/00 ; H04W24/02 ; H04W72/12 ; H04W72/121

Abstract:
Aspects presented herein may enable a network entity to configure a group of UEs to simultaneously transmit reference signals and to simultaneously transmit gradient vectors to the network entity, such that the network entity may receive the gradient vectors from the group of UEs as an aggregated gradient vector over the air. In one aspect, a base transmits, to a group of UEs, a configuration that configures the group of UEs to simultaneously transmit one or more group-common reference signals and to simultaneously transmit one or more gradient vectors associated with a federated learning procedure. The network entity receives, from the group of UEs, the one or more group-common reference signals and the one or more gradient vectors based on the configuration via multiple channels. The network entity calculates an average gradient vector based on the one or more group-common reference signals and the one or more gradient vectors.
Public/Granted literature
- US20230084883A1 GROUP-COMMON REFERENCE SIGNAL FOR OVER-THE-AIR AGGREGATION IN FEDERATED LEARNING Public/Granted day:2023-03-16
Information query