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

Graph node multi-tag classification method based on depth learning

A classification method and deep learning technology, applied in the field of multi-label classification of graph nodes based on deep learning, can solve the problems of low accuracy and achieve high accuracy

Inactive Publication Date: 2017-08-01
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this traditional multi-label classification algorithm is that the accuracy rate is low.

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 node multi-tag classification method based on depth learning
  • Graph node multi-tag classification method based on depth learning
  • Graph node multi-tag classification method based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the objectives, technical solutions and advantages of the present invention clearer, the following further describes the present invention in detail through specific embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention.

[0029] First, give a general description of the main steps in the classification method:

[0030] The load graph data module loads graph data saved in various formats into the memory and saves it in the form of a dictionary, where the key of the dictionary represents a certain node in the graph, and the value of the dictionary represents the sequence of neighbor nodes of the node.

[0031] The generating walking path module completes the random walk in the graph data and generates the walking path. The specific method is to randomly shuffle the sequence of nodes in the graph, and then...

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 node multi-tag classification method based on depth learning. The method comprises the steps that a graph data module is loaded, and graph data are analyzed and stored in the form of a dictionary; a walk path module is generated to complete random walk in the graph data, and a generated walk path is returned; a node eigenvector module is generated, and the walk path returned by the previous step, the specified vector representing dimension and the context window size are used as input to call a word2vec algorithm to calculate the eigenvector representation of each graph node; a training data module is generated, and nodes of a certain percentage are randomly selected from all graph nodes as training node data; for each node, the eigenvector and the tag sequence corresponding to the node are taken to form a two-tuple set as a training sample; and finally, a depth confidence network model is built. The graph node multi-tag classification algorithm proposed by the invention has higher correct rate than a traditional multi-tag classification algorithm.

Description

Technical field [0001] The present invention proposes a method for multi-label classification of nodes in the network using a deep learning algorithm deep belief network classification model, which involves the feature representation of the nodes in the network, the construction of the classification model of the deep belief network, and the generation of training data, etc. . Background technique [0002] Walk-based network representation learning algorithms, such as deepwalk, use the theoretical method of word2vec to compare the nodes in the network with the word units in natural language processing, and compare the connection paths in the network to natural language. A sentence being processed; using the method of solving the co-occurrence relationship between each word (that is, all conditional probability parameters) in the probabilistic language model to explore the connection structure between network nodes; using the method of generating word vectors to generate the netwo...

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): G06K9/62G06N3/08
CPCG06N3/084G06F18/28G06F18/2433G06F18/214
Inventor 李涛王次臣李华康
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