Hybrid federated learning method and architecture

A learning method and federated technology, applied in the field of financial technology and federated learning, which can solve problems such as the inaccuracy of federated learning models

Pending Publication Date: 2019-11-22
WEBANK (CHINA)
View PDF0 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of this application provides a hybrid federated learning method and architecture, which solves the problem of inaccurate federated learning models in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hybrid federated learning method and architecture
  • Hybrid federated learning method and architecture
  • Hybrid federated learning method and architecture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application. To illustrate, rather than limit, the technical solutions of the present application, the embodiments of the present application and the technical features in the embodiments can be combined without conflict.

[0028] During the operation of financial institutions (banking institutions, insurance institutions or securities institutions) (such as bank loan business, deposit business, etc.), the adjustment of many financial strategies depends on the results of federated learning on a large amount of financial transaction data. The adjustment of the corresponding financial strat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a hybrid federated learning method and architecture. The method is suitable for training a federated learning model with multiple groups of participants. The method comprises:for each group, jointly training a first federated learning model of each group according to data sets of participants in the group; fusing the first federated learning models of each group to obtaina second federated learning model, and sending the second federated learning model to participants in each group; and for each group, training according to the second federated learning model and thedata set of the participants in the group to obtain an updated first federated learning model, and returning to the step of fusing the first federated learning models of each group to obtain a secondfederated learning model until the model training is finished. When the method is applied to fintech, the accuracy of a federated learning model can be improved.

Description

technical field [0001] The present invention relates to the fields of financial technology (Fintech) and federated learning, in particular to a hybrid federated learning method and architecture. Background technique [0002] With the development of computer technology, more and more technologies (big data, distributed, blockchain (Blockchain), artificial intelligence, etc.) are applied in the financial field, and the traditional financial industry is gradually transforming into financial technology (Fintech). At present, the adjustment of many financial strategies in the field of financial technology relies on the results of federated learning on a large amount of financial transaction data, and the adjustment of corresponding financial strategies is likely to affect the profit and loss of financial institutions. Therefore, for a financial institution, the accuracy of its federated learning model is crucial. [0003] However, in the current scenario of applying federated le...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q40/04G06Q40/02
CPCG06Q40/02G06Q40/04
Inventor 程勇董苗波刘洋陈天健
Owner WEBANK (CHINA)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products