Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021144803 - CONTEXT-LEVEL FEDERATED LEARNING

Publication Number WO/2021/144803
Publication Date 22.07.2021
International Application No. PCT/IN2020/050047
International Filing Date 16.01.2020
IPC
G06N 20/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 99/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
G06F 9/50 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
50Allocation of resources, e.g. of the central processing unit
CPC
G06F 9/54
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
54Interprogram communication
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
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
Applicants
  • TELEFONAKTIEBOLAGET LM ERICSSON (PUBL) [SE]/[SE]
  • PEREPU, Satheesh Kumar [IN]/[IN] (SC)
Inventors
  • PEREPU, Satheesh Kumar
  • SENTHAMIZ SELVI, Arumugam
  • SARAVANAN, Mohan
Agents
  • DJ, Solomon
  • ANAND, Barnabas
  • RR, Nair
Priority Data
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) CONTEXT-LEVEL FEDERATED LEARNING
(FR) APPRENTISSAGE FÉDÉRÉ AU NIVEAU DU CONTEXTE
Abstract
(EN) A method performed by a local client computing device is provided. The method includes: training a local model using data from the local client computing device, resulting in a local model update; sending the local model update to a central server computing device; receiving from the central server computing device a first updated global model; determining that the first updated global model does not meet a local criteria, wherein determining that the first updated global model does not meet a local criteria comprises computing a score based on the first updated global model, wherein the score exceeds a threshold; in response to determining that the first updated global model does not meet a local criteria, sending to the central server computing device context information; and receiving from the central server computing device a second updated global model.
(FR) L'invention concerne un procédé exécuté par un dispositif informatique client local. Le procédé consiste à : entraîner un modèle local à l'aide de données provenant du dispositif informatique client local, conduisant à une mise à jour de modèle local ; envoyer la mise à jour de modèle local à un dispositif informatique serveur central ; recevoir du dispositif informatique serveur central un premier modèle global mis à jour ; déterminer que le premier modèle global mis à jour ne satisfait pas un critère local, la détermination du fait que le premier modèle global mis à jour ne satisfait pas un critère local comprenant le calcul d'un score sur la base du premier modèle global mis à jour, le score dépassant un seuil ; en réponse à la détermination du fait que le premier modèle global mis à jour ne satisfait pas un critère local, envoyer au dispositif informatique serveur central des informations de contexte ; et recevoir du dispositif informatique serveur central un second modèle global mis à jour.
Latest bibliographic data on file with the International Bureau