Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Tensor CP decomposition implementation method based on distributed environment

A technology of distributed environment and implementation method, which is applied in the direction of complex mathematical operations and can solve limited and other problems

Active Publication Date: 2018-06-15
YUNNAN UNIV
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional CP decomposition algorithm runs on a single machine. Although the program can process larger-scale data by improving the configuration of the machine, such improvement is limited after all.

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
  • Tensor CP decomposition implementation method based on distributed environment
  • Tensor CP decomposition implementation method based on distributed environment
  • Tensor CP decomposition implementation method based on distributed environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] The present invention is based on the ALS algorithm, improves the update of the factor matrix in each iteration process, realizes the update of the factor matrix based on the distributed environment, and improves the efficiency of tensor CP decomposition. figure 1 It is a specific implementation flow chart of factor matrix update in the implementation method of tensor CP decomposition based on distributed environment in the present invention. Such as figure 1 As shown, in the tensor CP decomposition implementation method based on the distributed environment of the present invention, the specific steps of factor matrix update include:

[0063] S101: Data collation:

[0064] Let the set D={1,2,...,N}-{n}, arrange the elements in the set D in ascending order, and record the jth element as d j , obviously there are N-1 elements in the set D, that is, j=1,2,...,N-1; let the matrix Y=X (n) (A (N) ⊙…⊙A (n+1) ⊙A (n-1) ⊙…⊙A (1) ), i.e. A (n) =YV.

[0065] S102: Split ...

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 tensor CP decomposition implementation method based on a distributed environment. A factor matrix A(n) in each iteration is updated based on an ALS algorithm, Y=X(n)(A(N)...A(n+1)A(n-1)...A(1)) is first calculated by splitting a Khatri-Rao product, then an outer product is calculated by parallel calculation, finally, a matrix Y and a matrix V are partitioned, partitionedmatrices corresponding to the matrix Y and the matrix V are distributed to a host of a Spark cluster by a Map operation, a matrix multiplication is performed by a Reduce operation, and then the multiplication results are sent to the host by the Map operation and merged by the Reduce operation to obtain A(n)=YV. The method implements tensor CP decomposition based on MapReduce and Spark technologies, thereby effectively improving the efficiency of tensor CP decomposition.

Description

technical field [0001] The invention belongs to the technical field of tensor decomposition, and more specifically relates to a method for realizing tensor CP decomposition based on a distributed environment. Background technique [0002] In recent years, the scale of data has grown rapidly in areas such as social networking, computing advertising, and e-commerce. In order to describe complex relationships, such as: friend relationships in social networks, computing advertising and the characteristics of each person in e-commerce, data based on high-dimensional spatial modeling emerges in large quantities. The emergence of these high-order data makes the traditional method of describing data in a two-dimensional manner by matrix gradually inapplicable, so a tool that can describe high-order relationships in high-dimensional data is urgently needed. [0003] As a generalization of matrices in high-dimensional spaces, tensors are better tools for describing high-order relatio...

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): G06F17/15
CPCG06F17/15
Inventor 周维麦超蔡莉何靖姚绍文
Owner YUNNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com