blank Quick help
blank Maintenance news

Scheduled maintenance

Regular maintenance outages:
between 05.00 and 05.15 hrs CET (Monday to Sunday).

Other outages
Availability
Register Forum

2022.02.11

More...
blank News flashes

News Flashes

New version of the European Patent Register – SPC proceedings information in the Unitary Patent Register.

2024-07-24

More...
blank Related links

Release notes
European Patent Register Assistant
European Patent Register Resource Book
European Patent Register – pocket guide
FAQ - European Patent Register
FAQ - Register Alert
Federated Register (Flyer)
Global Dossier (Flyer)
Register events
Deep link coverage
Federated Register content
The Patent Information Tour
Fair use charter

Extract from the Register of European Patents

EP About this file: EP4222647

EP4222647 - QUANTIZED FEEDBACK IN FEDERATED LEARNING WITH RANDOMIZATION [Right-click to bookmark this link]
StatusRequest for examination was made
Status updated on  07.07.2023
Database last updated on 03.09.2024
FormerThe international publication has been made
Status updated on  08.04.2022
Formerunknown
Status updated on  10.11.2021
Most recent event   Tooltip01.12.2023Change: Validation statespublished on 03.01.2024  [2024/01]
01.12.2023Change - extension statespublished on 03.01.2024  [2024/01]
Applicant(s)For all designated states
QUALCOMM INCORPORATED
ATTN: International IP Administration
5775 Morehouse Drive
San Diego, California 92121-1714 / US
[2023/32]
Inventor(s)01 / TAHERZADEH BOROUJENI, Mahmoud
San Diego, California 92121 / US
02 / YOO, Taesang
San Diego, California 92121 / US
03 / LUO, Tao
San Diego, California 92121 / US
04 / PEZESHKI, Hamed
San Diego, California 92121 / US
 [2023/32]
Representative(s)Tomkins & Co
5 Dartmouth Road
Dublin 6, D06 F9C7 / IE
[2023/32]
Application number, filing date21798913.622.09.2021
[2023/32]
WO2021US71545
Priority number, dateUS202063085748P30.09.2020         Original published format: US 202063085748 P
US20211744829821.09.2021         Original published format: US202117448298
[2023/32]
Filing languageEN
Procedural languageEN
PublicationType: A1 Application with search report
No.:WO2022072979
Date:07.04.2022
Language:EN
[2022/14]
Type: A1 Application with search report 
No.:EP4222647
Date:09.08.2023
Language:EN
The application published by WIPO in one of the EPO official languages on 07.04.2022 takes the place of the publication of the European patent application.
[2023/32]
Search report(s)International search report - published on:EP07.04.2022
ClassificationIPC:G06N3/04, G06N3/08, G06N3/063
[2023/32]
CPC:
G06N3/08 (EP,US); G06N3/045 (EP); H04L67/01 (US);
H04L67/12 (EP)
Designated contracting statesAL,   AT,   BE,   BG,   CH,   CY,   CZ,   DE,   DK,   EE,   ES,   FI,   FR,   GB,   GR,   HR,   HU,   IE,   IS,   IT,   LI,   LT,   LU,   LV,   MC,   MK,   MT,   NL,   NO,   PL,   PT,   RO,   RS,   SE,   SI,   SK,   SM,   TR [2023/32]
TitleGerman:QUANTISIERTES FEEDBACK BEIM FÖDERIERTEN LERNEN MIT RANDOMISIERUNG[2023/32]
English:QUANTIZED FEEDBACK IN FEDERATED LEARNING WITH RANDOMIZATION[2023/32]
French:RÉTROACTION QUANTIFIÉE DANS UN APPRENTISSAGE FÉDÉRÉ AVEC RANDOMISATION[2023/32]
Entry into regional phase17.01.2023National basic fee paid 
17.01.2023Designation fee(s) paid 
17.01.2023Examination fee paid 
Examination procedure17.01.2023Examination requested  [2023/32]
17.01.2023Date on which the examining division has become responsible
14.11.2023Amendment by applicant (claims and/or description)
Fees paidRenewal fee
30.08.2023Renewal fee patent year 03
Opt-out from the exclusive  Tooltip
competence of the Unified
Patent Court		 See the Register of the Unified Patent Court for opt-out data
Responsibility for the accuracy, completeness or quality of the data displayed under the link provided lies entirely with the Unified Patent Court.
Cited inInternational search[I]  - Horvath Samuel ET AL, "Natural Compression for Distributed Deep Learning", (20200213), URL: https://arxiv.org/pdf/1905.10988.pdf, (20220113), XP055878972 [I] 1-30 * abstract * * 1. Introduction * * 3. Natural compression * * B. Experimental setup *
 [A]  - MOHAMMAD MOHAMMADI AMIRI ET AL, "Federated Learning With Quantized Global Model Updates", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20200618), XP081698697 [A] 1-30 * abstract * * 1. Introduction *
 [A]  - Horvath Samuel ET AL, "FEDERATED LEARNING: STRATEGIES FOR IMPROVING COMMUNICATION EFFICIENCY", (20171030), pages 1 - 10, URL: https://arxiv.org/pdf/1610.05492.pdf, (20190124), XP055546999 [A] 1-30 * abstract * * 1. Introduction *
The EPO accepts no responsibility for the accuracy of data originating from other authorities; in particular, it does not guarantee that it is complete, up to date or fit for specific purposes.