Graph neural network training method and device
A neural network and training method technology, applied in the computer field, can solve problems such as computing resources and memory usage burden, achieve the effect of reducing memory usage and computing consumption, and ensuring accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] Multiple embodiments disclosed in this specification will be described below in conjunction with the accompanying drawings.
[0024] As mentioned earlier, a relational network graph can be abstracted to include a set of nodes and a set of edges, where nodes represent entities in the real world, and edges represent associations between entities. figure 1 A schematic diagram showing a relational network graph, where users are taken as nodes for example. As shown in the figure, users with associated relationships are connected by edges.
[0025] In recent years, the graph neural network model (or graph neural network, GNN network, GNN model) has developed rapidly, from the original graph convolutional neural network (Graph Convolutional Network, referred to as GCN) model to the graph neural network with attention mechanism Model, the effect of the model has been greatly improved. However, the introduction of attention mechanism also brings new challenges for graph sampli...
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