SYSTEM AND METHOD FOR FEDERATED LEARNING USING WEIGHT ANONYMIZED FACTORIZATION

리앙 케빈 제이 (Inventor), 엘-카미 모스타파 (Inventor), 메타 니킬 (Inventor), 하오 웨이투오 (Inventor), 이정원 (Inventor), 로렌스 카린 (Inventor)

Research output: Patent

Abstract

A federal machine-learning system includes a global server and client devices. The server receives updates of weight factor dictionaries and factor strength vectors from the clients, and generates a globally updated weight factor dictionary and a globally updated factor strength vector. A client device selects a group of parameters from a global group of parameters, and trains a model using a dataset of the client device and the group of selected parameters. The client device sends to the server a client-updated weight factor dictionary and a client-updated factor strength vector. The client device receives the globally updated weight factor dictionary and the globally updated factor strength vector, and retrains the model using the dataset of the client device, the group of parameters selected by the client device, and the globally updated weight factor dictionary and the globally updated factor strength vector.

Original languageEnglish (US)
Patent numberKR20210150293
IPCG06N 20/ 20 A I
Priority date01/13/21
StatePublished - Dec 10 2021

Fingerprint

Dive into the research topics of 'SYSTEM AND METHOD FOR FEDERATED LEARNING USING WEIGHT ANONYMIZED FACTORIZATION'. Together they form a unique fingerprint.

Cite this