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

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

Pending Publication Date: 2022-05-13
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing graph neural network pre-training models only focus on the features and structural information at the node or graph level, ignoring the time information carried by the edges in the graph.

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
  • Pre-training method based on dynamic graph neural network
  • Pre-training method based on dynamic graph neural network
  • Pre-training method based on dynamic graph neural network

Examples

Experimental program
Comparison scheme
Effect test

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...

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 pre-training method based on a dynamic graph neural network learns node representation from three aspects of time, structure and semantics, and comprises the following steps: determining the size of a sampling sub-graph according to actual requirements and system performance, and performing sub-graph sampling on large-scale dynamic graph data by using a time sensitive sampling algorithm to obtain a sub-graph; for the sub-graph, performing covering processing on the sub-graph by using a time-sensitive edge covering algorithm and a node feature covering algorithm to obtain a processed new sub-graph; a dynamic graph generation algorithm is combined with a GNN model to predict covering edges and covering node features of the sub-graphs, optimal parameters are stored, and the pre-training process is ended; and loading the optimal parameters, and performing fine adjustment on the predicted graph data according to different downstream tasks to obtain a final result. According to the method, large-scale dynamic graph data can be processed, and compared with other pre-training methods, the method is higher in expression ability, learned nodes are more accurate in expression, and the method can be better applied to various downstream tasks.

Description

technical field [0001] The invention relates to the field of graph neural networks in deep learning, in particular to a pre-training method based on dynamic graph neural networks. Background technique [0002] A graph or network is an effective abstraction of real-world data structures, such as citation networks, social networks, protein networks, transportation networks, etc. Traditional network analysis methods require researchers to manually extract features, depending on network type, researcher's experience and specific tasks. In recent years, with the continuous development of deep learning, the GNN model has made breakthroughs in various graph mining tasks (such as node classification, link prediction, etc.) by virtue of the advantages of end-to-end learning and powerful reasoning methods. GNN takes node features and graph structural features as input, and through multi-layer information transfer (ie, graph convolution), obtains low-dimensional dense node representat...

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): G06V10/764G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/048G06N3/045G06F18/2415G06F18/214
Inventor 陈可佳张嘉俊
Owner NANJING UNIV OF POSTS & TELECOMM
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