Pre-training method based on dynamic graph neural network
A neural network and dynamic graph technology, applied in the field of graph neural network, can solve problems such as ignoring time information, achieve good application, strong expressive ability, and accurate node representation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0051] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0052] The specific use process of this method includes two stages of data processing and model training. In the data processing stage, users need to specify the graph data format before model training, provide graph data according to the data format required by the model, and split the data set into training set, verification set, and test set. Model training can be roughly divided into two processes, namely pre-training and fine-tuning. The pre-training process is the training phase of the model. In order to capture the characteristics of the graph itself, the graph data is used for pre-training. See steps 2 and 3 for details; the fine-tuning stage is the model Fine-tune the use process according to different task requirements, see step 4 for details.
[0053] The pre-training method described in the embodiment of the present inve...
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