Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LONGITUDINAL FEDERAL PREDICTION OPTIMIZATION METHOD AND DEVICE, MEDIUM, AND COMPUTER PROGRAM PRODUCT
Document Type and Number:
WIPO Patent Application WO/2023/024350
Kind Code:
A1
Abstract:
A longitudinal federal prediction optimization method and device, a medium, and a computer program product. The method comprises: extracting a first-party sample to be predicted, and acquiring a first-party model prediction result generated by performing model prediction on said first-party sample by means of a target prediction model; performing federal interaction with a second device to enable the second device to determine a second-party sample to be predicted, and using a target residual boosting model to perform model prediction on said second-party sample to obtain a second-party model prediction result (S20); acquiring a first-party model weight corresponding to the target prediction model, and receiving the second-party model prediction result sent by the second device and a second-party model weight corresponding to the target residual boosting model (S30); and performing weighted aggregation on the first-party model prediction result and the second-party model prediction result on the basis of the first-party model weight and the second-party model weight to obtain a target federal prediction result (S40).

More Like This:
WO/2021/247764STRUCTURED CONVOLUTIONS AND ASSOCIATED ACCELERATION
WO/2023/024252NETWORK MODEL TRAINING METHOD AND APPARATUS, ELECTRONIC DEVICE AND READABLE STORAGE MEDIUM
WO/2022/037955METHOD FOR DETERMINING AN INDICATOR OF A TECHNICAL SYSTEM, DETERMINATION UNIT AND CONSTRUCTION SYSTEM
Inventors:
WAN SHENG (CN)
GAO DASHAN (CN)
JU CE (CN)
TAN BEN (CN)
YANG QIANG (CN)
Application Number:
PCT/CN2021/139641
Publication Date:
March 02, 2023
Filing Date:
December 20, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
WEBANK CO LTD (CN)
International Classes:
G06N3/08; G06N3/04; G06N20/00
Foreign References:
CN113673700A2021-11-19
CN110633805A2019-12-31
CN113205863A2021-08-03
CN113051557A2021-06-29
CN112329073A2021-02-05
CN111460511A2020-07-28
Other References:
DASHAN GAO; BEN TAN; CE JU; VINCENT W. ZHENG; QIANG YANG: "Privacy Threats Against Federated Matrix Factorization", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 3 July 2020 (2020-07-03), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081714185
Attorney, Agent or Firm:
CENFO INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: METHOD FOR OPTIMIZING VERTICAL FEDERATED PREDICTION, DEVICE, MEDIUM, AND COMPUTER PROGRAM PRODUCT

Next Patent: USE OF GGPP BINDING AND ALLOSTERIC ACTIVATION OF HUMAN FBP1 IN PREPARATION OF ANTI-HEPATOCELLULAR CA...