Invention Publication
- Patent Title: METHOD AND SYSTEM FOR FEDERATED LEARNING
-
Application No.: EP23198714.0Application Date: 2023-09-21
-
Publication No.: EP4345697A1Publication Date: 2024-04-03
- Inventor: KIM, Minyoung , HOSPEDALES, Timothy
- Applicant: Samsung Electronics Co., Ltd.
- Applicant Address: KR Suwon-si, Gyeonggi-do 16677 129, Samsung-ro Yeongtong-gu
- Agency: Appleyard Lees IP LLP
- Priority: GB202214033 20220926
- Main IPC: G06N7/01
- IPC: G06N7/01 ; G06N3/098
Abstract:
Broadly speaking, embodiments of the present techniques provide a method for training a machine learning, ML, model to update global and local versions of a model. We propose a novel hierarchical Bayesian approach to Federated Learning (FL), where our models reasonably describe the generative process of clients' local data via hierarchical Bayesian modeling: constituting random variables of local models for clients that are governed by a higher-level global variate. Interestingly, the variational inference in our Bayesian model leads to an optimisation problem whose block-coordinate descent solution becomes a distributed algorithm that is separable over clients and allows them not to reveal their own private data at all, thus fully compatible with FL.
Information query