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

Sgcnn: structural graph convolutional neural network

A convolutional neural network and subgraph technology, applied in the field of SGCNN: structured graph-based convolutional neural network, can solve the problem that the graph kernel is not enough to complete

Pending Publication Date: 2019-04-05
SIEMENS AG
View PDF1 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, graph kernels are not sufficient for this task

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
  • Sgcnn: structural graph convolutional neural network
  • Sgcnn: structural graph convolutional neural network
  • Sgcnn: structural graph convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The following disclosure describes the invention in terms of several embodiments related to methods, systems, and apparatus related to structured graph-based convolutional neural networks (SGCNNs) capable of The hierarchy performs graph-invariant learning tasks. The SGCNN architecture performs training tasks at the graph / subgraph level. The architecture provides many other benefits over traditional solutions, including new graph feature compression for graph-based learning based on Node2Vec embeddings; path-based neighbor nodes that aggregate vertex-domain neighbor node information onto subgraphs Ensemble methods; and convolution kernels for subgraphs that can perform graph-invariant convolution operations on graphs or subgraphs.

[0028] In the following disclosure, a graph is defined as G=(V,E), where V is the set of vertices and E is the set of edges. In some embodiments, graph edges may be weighted and directed. However, for simplicity, the following description ...

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

A computer-implemented method for learning structural relationships between nodes of a graph includes the steps: generating a knowledge graph comprising nodes representing a system and applying a graph-based convolutional neural network (GCNN) to the knowledge graph to generate feature vectors describing structural relationships between the nodes. The GCNN comprises: (i) a graph feature compression layer configured to learn subgraphs representing embeddings of the nodes of the knowledge graph into a vector space, (ii) a neighbor nodes aggregation layer configured to derive neighbor node feature vectors for each subgraph and aggregate the neighbor node feature vectors with their corresponding subgraphs to yield aggregated subgraphs, and (iii) a subgraph convolution layer configured to generate the feature vectors based on the aggregated subgraphs. Functional groups of components included in the system may then be identified based on the plurality of feature vectors.

Description

[0001] Cross References to Related Applications [0002] This application claims U.S. Provisional To the benefit of the application, all of these documents are hereby incorporated by reference in their entirety. technical field [0003] The present invention generally relates to a method, system, and apparatus related to convolutional neural networks (CNNs) involving learning tasks designed for graph invariance at the layer level and sub-layer level. The disclosed methods, systems and apparatus can be applied, for example, to analyze functional data corresponding to a digital twin. Background technique [0004] Machine learning and convolutional neural networks (CNNs) have achieved great success in solving clustering and classification problems such as grid-structured Euclidean data (1D signals such as time series and 2D datasets such as images). However, many other real-world problems require learning on unstructured data. For example, in the field of engineering, many n...

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): G06N3/04G06N3/08G06F17/50
CPCG06N3/08G06F30/15G06F30/20G06N3/045G06N5/022G06Q10/04G06Q50/01G06N5/046G06F17/15G06N20/00G06F16/9024G06F18/21
Inventor 阿基梅德斯·马丁内斯·卡内多万江布莱克·波拉德
Owner SIEMENS AG
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