A Memic algorithm-based network representation learning method
A technology of network representation and learning methods, applied in computing, computational models, biological models, etc., can solve the problems of indistinguishable representation vectors, indistinguishable network representations, and small distances between classes
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0055] Genes represent the representation vectors of each node in the network, and the set of genes is a real-coded individual; the set of real-coded individuals is a population. The nodes of the same category are the nodes with the same label in the K-means clustering result.
[0056] The function that can be used to evaluate the fitness function value of a real number coded individual can be any function as long as it can achieve the function of maintaining the community property, for example, it can be a module density function or a modularity function.
[0057] Central nodes include neighbor central nodes and central nodes of the same category, among which, neighbor central nodes: include obtaining the representation vector set N of each network node and the degree set D of each network node’s neighbor nodes, and normalizing D got a D norm ; For the representation vector set N with weight D norm The weighted summation is performed to obtain the neighbor central node C of...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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