Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
TRAINING SAMPLE CONSTRUCTION METHOD, APPARATUS, AND DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/022024
Kind Code:
A1
Abstract:
A training sample construction method, apparatus, and device, and a computer-readable storage medium. The method comprises the following steps: acquiring a local training sample of a first participant, and converting the local training sample into a preset data form to obtain a local sample representation corresponding to the local training sample (S10); receiving a non-overlapping sample representation sent by a second participant, the non-overlapping sample representation being obtained after the second participant converts a non-overlapping training sample in local training samples of the second participant into the same data form as the local sample representation of the first participant (S20); calculating, on the basis of representation data in the non-overlapping sample representation and representation data in the local sample representation, a supplementary sample representation corresponding to the local sample representation (S30); and adding the supplementary sample representation into the local sample representation to obtain a complete sample representation, and participating in longitudinal federated learning on the basis of the complete sample representation (S40).

More Like This:
WO/2021/163362SYSTEMS AND METHODS FOR SECURE PROCESSING OF EYE TRACKING DATA
JP2023018517MACHINE LEARNING MODEL PROVIDING SYSTEM, AND MACHINE LEARNING MODEL PROVIDING METHOD
WO/2023/205204CLASSIFICATION PROCESS SYSTEMS AND METHODS
Inventors:
KANG YAN (CN)
Application Number:
PCT/CN2021/094939
Publication Date:
February 03, 2022
Filing Date:
May 20, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
WEBANK CO LTD (CN)
International Classes:
G06N20/00
Foreign References:
CN111860868A2020-10-30
CN110750520A2020-02-04
CN111178538A2020-05-19
CN111046433A2020-04-21
US20200218937A12020-07-09
Other References:
KEWEI CHENG; TAO FAN; YILUN JIN; YANG LIU; TIANJIAN CHEN; QIANG YANG: "SecureBoost: A Lossless Federated Learning Framework", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 25 January 2019 (2019-01-25), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081008079
Attorney, Agent or Firm:
CENFO INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: METHOD FOR CONTROLLING NETWORKING OF LASER TERMINAL GUIDANCE AIRCRAFTS

Next Patent: BRIGHTNESS COMPENSATION METHOD, APPARATUS AND DEVICE FOR DISPLAY PANEL