Graph node label information prediction method and device and electronic equipment
A technology of node labels and prediction methods, applied in neural learning methods, special data processing applications, biological neural network models, etc., can solve problems such as inaccurate prediction results, too few marked nodes, and unstable iterative results
Active Publication Date: 2021-01-15
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, the prediction methods of graph node label information in the prior art often have situations such as unstable iteration results and too few marked nodes in the graph to be learned. inaccurate result
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0033] The following is a brief description of the technical field involved in the scheme of the present application:
[0034] Image processing (Image Processing), also known as image processing, is a technology that uses computers to analyze images to achieve the desired results. Image processing technology is widely used, and mainly plays an extremely important ro...
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
Login to View More Abstract
The invention discloses a graph node label information prediction method and device and electronic equipment, and relates to the technical field of artificial intelligence such as deep learning and machine learning. According to the scheme, the method comprises the steps of obtaining node features of labeled nodes, node features of unlabeled nodes and node label features of labeled nodes in a to-be-learned graph; inputting the node features of the labeled nodes, the node features of the unlabeled nodes and the node label features of the labeled nodes into a trained graph neural convolutional network model to obtain state information of the unlabeled nodes; and predicting prediction node label information of the unlabeled nodes according to the state information of the unlabeled nodes. According to the method, the node features of all the nodes and the node label features of the labeled nodes can serve as input of the graph neural convolutional network model, the state information of the unlabeled nodes is obtained, then the prediction node label information of the unlabeled nodes is predicted, and the performance of a semi-supervised graph node classification task is improved.
Description
technical field [0001] The embodiments of the present application generally relate to the technical field of image processing, and more specifically relate to the technical fields of artificial intelligence such as deep learning and machine learning. Background technique [0002] In recent years, with the explosive growth of Internet data, various resources have also grown exponentially. Among them, graph (Graph) resources, as one of the important resources, have emerged in large numbers on the Internet, and graph learning is also gradually It has become a core field in Machine Learning (ML). In particular, as a common problem in the graph learning process, the semi-supervised (Semi Supervised) graph node classification task has received more and more attention. [0003] However, the prediction methods of graph node label information in the prior art often have situations such as unstable iteration results and too few marked nodes in the graph to be learned. The result is ...
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
Login to View More IPC IPC(8): G06F16/901G06F16/906G06N3/04G06N3/08
CPCG06F16/9024G06F16/906G06N3/08G06N3/045
Inventor 施云生黄正杰冯仕堃黄世维何径舟
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD