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

Graph attention network inductive learning method based on graph sampling

A learning method and attention technology, applied in the field of machine learning, can solve the problem of large-scale graph data set classification without public disclosure

Pending Publication Date: 2021-07-06
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, in the prior art, there is no public disclosure of how the inductive learning algorithm of graph attention network based on graph sampling can effectively solve the classification problem of large graph datasets.

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
  • Graph attention network inductive learning method based on graph sampling
  • Graph attention network inductive learning method based on graph sampling
  • Graph attention network inductive learning method based on graph sampling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052]The present invention proposes a method of summarizing the study method based on the graphic sample, and the specific scheme is as follows.

[0053] Such as figure 1 As shown, a graphic scales based on map sample sampling are summarized, mainly including two parts of the graph spam and diagram training procedures.

[0054] Among them, the pattern samples mainly include the following steps:

[0055] S1, enter the map to be sampled and set the random swing sampler parameters. The specific operation of this step can be further clear.

[0056] S11, input to the graph g (v, e) to be sampled, where V represents a collection of sample points in Figure G, E represents the connection edge set between sample points in Figure G;

[0057] S12, set randomly walking sampler parameters, the parameters comprise Root number R and randomly travel length h.

[0058] S2, using a random travel sampler to randomly swim the input map, obtain a sub-map after the sample. The specific operation of th...

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 graph attention network inductive learning method based on graph sampling, which mainly comprises two parts, namely a graph sampling process and a graph training process, and is characterized in that a plurality of sub-graphs are sampled from an original data set large graph by using a random walk sampler to form mini batch, and then the mini batch is input into a graph attention network for training; and according to the method, a big data set is split into small data sets, and the number of training rounds is increased, so that the performance of the method is remarkably improved, and the method is ensured to have good robustness. The method can also serve as the basis of the technical thought, and has reference value and deployment significance for researchers in the industry to design related algorithms in the future.

Description

Technical field [0001] The present invention is a method of summarizing the study method for the figure, specifically, based on the map sampling, the imaging, the learning method, involving the field of machine learning. Background technique [0002] The picture as a mathematical tool that describes the data structure has always been considered as an effective method of characterizing the intrinsic relationship of the data entity. In the current research and application products, the research of map structure data is also very important. . As deep learning has gradually become human research and implementing artificial intelligence the most important tools, more and more research began to apply depth learning methods to the field of map data. [0003] The traditional depth learning approach is the data under the European space, which generally has a very rule of space structure; the figure data is usually taken from real life, which belongs to the data under non-Ou Space. The spa...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214G06F18/241
Inventor 胡海峰刘潇吴建盛朱燕翔
Owner NANJING UNIV OF POSTS & TELECOMM
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