US 12,231,490 B2
Uses of coded data at multi-access edge computing server
Mustafa Riza Akdeniz, San Jose, CA (US); Arjun Anand, Milpitas, CA (US); Ravikumar Balakrishnan, Beaverton, OR (US); Sagar Dhakal, Los Altos, CA (US); and Nageen Himayat, Fremont, CA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Appl. No. 18/550,856
Filed by Intel Corporation, Santa Clara, CA (US)
PCT Filed Jun. 9, 2022, PCT No. PCT/US2022/032873
§ 371(c)(1), (2) Date Sep. 15, 2023,
PCT Pub. No. WO2022/261353, PCT Pub. Date Dec. 15, 2022.
Claims priority of provisional application 63/208,831, filed on Jun. 9, 2021.
Prior Publication US 2024/0155025 A1, May 9, 2024
Int. Cl. G06F 13/00 (2006.01); G06N 3/098 (2023.01); H04L 67/10 (2022.01); H04L 67/289 (2022.01)
CPC H04L 67/10 (2013.01) [G06N 3/098 (2023.01); H04L 67/289 (2013.01)] 25 Claims
OG exemplary drawing
 
1. An apparatus of an edge computing node to be operated in an edge computing network, the apparatus including:
an interconnect interface to connect the apparatus to one or more components of the edge computing node; and
one or more processors to:
decode messages from a plurality of clients within the edge computing network, the messages including respective coded data for respective ones of the plurality of clients;
compute estimates of metrics related to a global model for federated learning using the coded data, the metrics including a gradient on the coded data;
use the metrics to update the global model to generate an updated global model, wherein the one or more processors are to update the global model by calculating the gradient on the coded data based on a linear fit of the global model to estimated labels from the federated learning; and
send a message including the updated global model for transmission to at least some of the clients.