Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022251885 - BI-DIRECTIONAL COMPRESSION AND PRIVACY FOR EFFICIENT COMMUNICATION IN FEDERATED LEARNING

Publication Number WO/2022/251885
Publication Date 01.12.2022
International Application No. PCT/US2022/072659
International Filing Date 31.05.2022
IPC
H03M 7/30 2006.1
HELECTRICITY
03BASIC ELECTRONIC CIRCUITRY
MCODING, DECODING OR CODE CONVERSION, IN GENERAL
7Conversion of a code where information is represented by a given sequence or number of digits to a code where the same information is represented by a different sequence or number of digits
30Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
G06N 3/08 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 20/20 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
20Ensemble learning
CPC
G06N 3/063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
H03M 7/3057
HELECTRICITY
03BASIC ELECTRONIC CIRCUITRY
MCODING; DECODING; CODE CONVERSION IN GENERAL
7Conversion of a code where information is represented by a given sequence or number of digits to a code where the same ; , similar or subset of; information is represented by a different sequence or number of digits
30Compression
3057Distributed Source coding, e.g. Wyner-Ziv, Slepian Wolf
Applicants
  • QUALCOMM INCORPORATED [US]/[US]
Inventors
  • REISSER, Matthias
  • TRIASTCYN, Aleksei
  • LOUIZOS, Christos
Agents
  • TRANSIER, Nicholas
  • READ, Randol
Priority Data
2021010035528.05.2021GR
PCT/US2022/07259926.05.2022US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) BI-DIRECTIONAL COMPRESSION AND PRIVACY FOR EFFICIENT COMMUNICATION IN FEDERATED LEARNING
(FR) COMPRESSION BIDIRECTIONNELLE ET CONFIDENTIALITÉ POUR UNE COMMUNICATION EFFICACE DANS UN APPRENTISSAGE FÉDÉRÉ
Abstract
(EN) Certain aspects of the present disclosure provide techniques for performing federated learning, including receiving a global model from a federated learning server; determining an updated model based on the global model and local data; and sending the updated model to the federated learning server using relative entropy coding.
(FR) Certains aspects de la présente divulgation concernent des techniques pour effectuer un apprentissage fédéré, consistant à recevoir un modèle global à partir d'un serveur d'apprentissage fédéré; à déterminer un modèle mis à jour sur la base du modèle global et de données locales; et à envoyer le modèle mis à jour au serveur d'apprentissage fédéré à l'aide d'un codage entropique relatif.
Latest bibliographic data on file with the International Bureau