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

Method for processing graph data through quantum graph convolutional neural network

A convolutional neural network and graph data technology, which is applied in the fields of artificial intelligence, machine learning and quantum computing, can solve problems such as different local structures, quantum neural network models not suitable for graph data, and graph data irregularities, etc., to achieve enhanced expression Ability, Efficient Aggregation, Effects of Extended Applicability

Active Publication Date: 2021-07-23
BEIHANG UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Graph data is irregular. Different from image and text data, the local structure of each node in graph data is different, which makes the existing quantum neural network model not suitable for direct application to graph data.

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
  • Method for processing graph data through quantum graph convolutional neural network
  • Method for processing graph data through quantum graph convolutional neural network
  • Method for processing graph data through quantum graph convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] refer to figure 1 , the present embodiment provides a method for processing graph data by a quantum graph convolutional neural network, comprising the following steps:

[0041]S1: Obtain the image data of the image processing task in machine learning, identify the graph structure of the image to obtain the input image data, establish an image processing data set, including the input image data and its corresponding target output, and divide the data set into training set and test set;

[0042] S2: Preprocess the input graph data in the dataset and uniformly encode the nodes and edges in the input graph data;

[0043] In this embodiment, the preprocessing of graph data mainly includes: preprocessing dirty data that contains missing values, inconsistent formats, logic errors, and non-actual requirements; expanding the dimension of input data that does not meet the dimension requirements, so as to The dimension of the input data is equal to the dimension that can be enc...

Embodiment 2

[0099] Such as Figure 6 As shown, the present embodiment also provides a training method for a quantum graph convolutional neural network, comprising the following steps:

[0100] S1: Obtain the training data set of the machine learning task, preprocess and uniformly encode the input image data;

[0101] S2: Initialize the parameters of the quantum graph convolutional neural network model constructed in Example 1;

[0102] S3: Determine the data type of the graph data in the training set, and prepare or input the quantum state according to different data types; among them, for the classical graph data, use the quantum state preparation method to encode it into qubits of corresponding information; for quantum data, which can be read directly as input data;

[0103] S4: Input the output quantum state to the quantum graph convolution layer of the quantum graph convolution module of the quantum graph convolutional neural network model and run it;

[0104] S5: Input the operati...

Embodiment 3

[0109] This embodiment provides a method of using the quantum graph convolutional neural network of the present invention to process graph data to realize a graph classification task, including:

[0110] Obtain the dataset needed to implement the graph classification task;

[0111] Call the last saved quantum graph convolutional neural network model after training;

[0112] Input the obtained data to be classified into the quantum graph convolutional neural network model for classification, and obtain the classification result of the machine learning graph classification task.

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 belongs to the field of artificial intelligence, machine learning and quantum computing, and relates to a method for processing graph data through a quantum graph convolutional neural network. The method comprises preparing the preprocessed data into a plurality of quantum bits; constructing a quantum graph convolutional neural network model having a quantum bit input module, a quantum graph convolution module, a quantum pooling module, a quantum bit measurement module and a network optimization updating module; and iteratively training the model for multiple times and optimizing the parameters of quantum gates in the model, so that an output result reaches target output as much as possible, and a machine learning task is realized. According to the method, the non-Euclidean spatial data type machine learning task can be effectively processed by using the advantages of quantum calculation and the neural network, so that the quantum neural network is not limited to only processing structured data, and the application range of quantum machine learning is greatly expanded. In addition, the model is easy to package, has strong generalization performance, and can be expanded according to different graph data structures.

Description

technical field [0001] The invention belongs to the fields of artificial intelligence, machine learning and quantum computing, and in particular relates to a method for processing graph data by a quantum graph convolutional neural network. Background technique [0002] In the past ten years, the rapid rise of machine learning and deep learning has become the cornerstone of technology in the era of big data. Artificial neural networks have achieved great success in information processing, automation, engineering, medicine and other fields. With the continuous development of information technology, informatization has closely linked various industries, and industrial data has exploded. This growth is not only the growth of data volume, but also the growth of data types, structures and production speeds. Memory resources are very demanding, causing machine learning to encounter computational bottlenecks when processing high-dimensional data. [0003] Quantum properties such as...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06N10/00
CPCG06N3/08G06N10/00G06N3/045G06F18/241
Inventor 吕金虎高庆郑瑾刘克新王振乾吕颜轩
Owner BEIHANG 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