The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Apr. 04, 2023

Filed:

Sep. 08, 2020
Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Shiqiang Wang, White Plains, NY (US);

Georgios Kollias, White Plains, NY (US);

Theodoros Salonidis, Wayne, PA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 20/20 (2019.01); G06N 3/00 (2023.01); G06F 18/23 (2023.01); G06F 18/2115 (2023.01); G06F 18/214 (2023.01);
U.S. Cl.
CPC ...
G06N 20/20 (2019.01); G06F 18/2115 (2023.01); G06F 18/2148 (2023.01); G06F 18/23 (2023.01);
Abstract

Using locality sensitive hashing in federated machine learning. A server receives from clients locality sensitive hash (LSH) vectors. In one embodiment, the server groups the clients into clusters, based on the LSH vectors; the server selects a subset of the clients, by choosing at least one client from each of the clusters. In another embodiment, the server finds a subset of the clients, by minimize gradient divergence for the subset of the clients. The server receives from selected clients LSH vectors computed based on parameter vectors of updated models, and based on LSH vectors the server determines whether the updated models are sufficiently different from a model being trained; in response to determining that the updated models are sufficiently different from the model, the server requests the selected clients to send the parameter vectors to the server.


Find Patent Forward Citations

Loading…