Method and device for training graphic neural network model
A neural network model and network graph technology, applied in biological neural network models, neural learning methods, etc., can solve the problems that machines cannot accommodate data and the training efficiency of GNN models is low, so as to reduce machine requirements and improve training efficiency.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0045] The following describes the solutions provided in this specification with reference to the drawings.
[0046] figure 1 This is a schematic diagram of an implementation scenario of an embodiment disclosed in this specification. This implementation scenario involves the training of the graph neural network model. Specifically, the graph neural network model is trained using a pre-established relational network diagram. The relational network graph includes multiple nodes and connecting edges between the nodes, each node has its own corresponding node number, and each connecting edge has its own corresponding edge number. To figure 1 Take the relationship network diagram in as an example. The relationship network diagram includes node 11, node 21, node 22, node 23, node 31, node 32, node 33, node 34, node 35, node 41, and between node 11 and node 21. There is a connecting edge, but there is no connecting edge between the node 21 and the node 23, the edge number of the connec...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap