Title:
METHOD AND SYSTEM FOR FEDERATED LEARNING
Document Type and Number:
WIPO Patent Application WO/2024/072017
Kind Code:
A1
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.
Inventors:
KIM MINYOUNG (GB)
HOSPEDALES TIMOTHY (GB)
HOSPEDALES TIMOTHY (GB)
Application Number:
PCT/KR2023/014863
Publication Date:
April 04, 2024
Filing Date:
September 26, 2023
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06N20/20; G06N3/098
Foreign References:
| CN111898764A | 2020-11-06 |
Other References:
XU ZHANG: "Personalized Federated Learning via Variational Bayesian Inference", PROCEEDINGS OF THE 39 TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING, PMLR, vol. 162, 1 January 2022 (2022-01-01), XP093156682
JOEY HONG; BRANISLAV KVETON; MANZIL ZAHEER; MOHAMMAD GHAVAMZADEH: "Hierarchical Bayesian Bandits", ARXIV.ORG, 5 March 2022 (2022-03-05), XP091192272
YUYANG DENG; MOHAMMAD MAHDI KAMANI; MEHRDAD MAHDAVI: "Adaptive Personalized Federated Learning", ARXIV.ORG, 6 November 2020 (2020-11-06), XP081797252
NIKITA KOTELEVSKII; MAXIME VONO; ERIC MOULINES; ALAIN DURMUS: "FedPop: A Bayesian Approach for Personalised Federated Learning", ARXIV.ORG, 7 June 2022 (2022-06-07), XP091242428
MINYOUNG KIM; TIMOTHY HOSPEDALES: "FedHB: Hierarchical Bayesian Federated Learning", ARXIV.ORG, 8 May 2023 (2023-05-08), XP091504906
JOEY HONG; BRANISLAV KVETON; MANZIL ZAHEER; MOHAMMAD GHAVAMZADEH: "Hierarchical Bayesian Bandits", ARXIV.ORG, 5 March 2022 (2022-03-05), XP091192272
YUYANG DENG; MOHAMMAD MAHDI KAMANI; MEHRDAD MAHDAVI: "Adaptive Personalized Federated Learning", ARXIV.ORG, 6 November 2020 (2020-11-06), XP081797252
NIKITA KOTELEVSKII; MAXIME VONO; ERIC MOULINES; ALAIN DURMUS: "FedPop: A Bayesian Approach for Personalised Federated Learning", ARXIV.ORG, 7 June 2022 (2022-06-07), XP091242428
MINYOUNG KIM; TIMOTHY HOSPEDALES: "FedHB: Hierarchical Bayesian Federated Learning", ARXIV.ORG, 8 May 2023 (2023-05-08), XP091504906
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF: