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

Graph convolutional neural network pooling method based on adaptive filtering

A convolutional neural network and adaptive filtering technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as inability to identify pharmacophore, and achieve high classification accuracy, better comprehensive performance, and comprehensive Excellent performance

Pending Publication Date: 2022-03-11
HEBEI UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When only using a low-pass filter for such molecules, the discriminant information for the entire graph is over-smoothed and the pharmacophore cannot be identified

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 convolutional neural network pooling method based on adaptive filtering
  • Graph convolutional neural network pooling method based on adaptive filtering
  • Graph convolutional neural network pooling method based on adaptive filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The technical solutions of the present invention are further explained below with reference to the embodiments and the accompanying drawings, but this is not intended to limit the protection scope of the present application.

[0025] The present invention provides a graph convolutional neural network pooling method (method for short) based on adaptive filtering, which includes the following two parts:

[0026] The first part, the convolution operation based on Self-adaptive Filtering with Graph Convolutional Networks (SFGCN): design low-pass filters, high-pass filters and band-pass filters in the frequency domain, and combine each The filter is converted into the corresponding spatial domain convolution kernel; each spatial domain convolution kernel is convolved through a graph convolutional neural network to obtain the embedding matrix corresponding to each filter; each embedding matrix is ​​summed to obtain the total embedding matrix;

[0027] 1) Design the low-pass f...

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 relates to a graph convolutional neural network pooling method based on adaptive filtering, and provides an adaptive filtering graph convolutional neural network SFGCN and a pooling operation SFGPool of the adaptive filtering graph convolutional neural network, the SFGCN is provided with a low-pass filter, a high-pass filter and a band-pass filter, the input of the pooling operation is enhanced, and the pooling operation of the adaptive filtering graph convolutional neural network is enhanced. Compared with a traditional graph convolutional network, intermediate-frequency and high-frequency information is supplemented, information loss is prevented, and the fitting capability of the network is enhanced; two learnable parameters are introduced into the adaptive filtering graph convolutional neural network, frequency characteristics of a filter can be adaptively adjusted in the training process, and contribution of each frequency band can be controlled through the learnable parameters for different graph classification tasks.

Description

technical field [0001] The invention belongs to the technical field of graph data processing, in particular to a graph convolution neural network pooling method based on adaptive filtering. Background technique [0002] In recent years, graph neural networks (GNNs) have achieved great success in many graph data tasks such as node classification, node clustering, link prediction, and graph segmentation, and these results demonstrate that GNNs can effectively learn node embeddings. While convolutional neural networks (CNNs) with pooling layers can efficiently downsample signals (such as image and video data) that reside on regular grids, while graph data is of irregular topology, so the CNN’s Pooling methods are not suitable for graph classification tasks. The core of the graph classification task is to learn a good representation of the entire graph. At present, the innovation of GNN is mainly focused on the design of the convolutional layer, resulting in a graph convolution...

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): G06N3/04G06N3/08
CPCG06N3/082G06N3/045
Inventor 顾军华李鑫航杨亮张亚娟牛炳鑫郑子辰李宁宁
Owner HEBEI UNIV OF TECH
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