Network representation learning method and device, electronic equipment and readable storage medium
A learning method and representation technology, applied in the computer field, can solve problems such as low accuracy of representation vectors, failure to consider local and global characteristics at the same time, and achieve high accuracy
Active Publication Date: 2021-05-04
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, since the scheme does not consider the local and global characteristics of each node in the network at the same time, the accuracy of the obtained representation vector is low
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
[0068] Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present application, and should not be construed as limiting the present invention.
[0069] Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the word "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and / or groups thereof. It will be u...
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 provides a network representation learning method and device, electronic equipment and a readable storage medium. The method comprises steps of carrying out the graph segmentation of a to-be-processed network graph, and obtaining at least two first sub-graphs; constructing a first thumbnail sub-graph corresponding to each first sub-graph; performing network representation learning on each first sub-graph to obtain a first representation vector of each node in each first sub-graph, and performing network representation learning on the first thumbnail sub-graph to obtain a second representation vector of each node in the first thumbnail sub-graph; and based on the first representation vector of each node in each first sub-graph and the second representation vector of each node in the first thumbnail sub-graph, obtaining a target representation vector of each node in the to-be-processed network graph. Since the target representation vector obtained by the scheme contains the local structure feature and the global structure feature of the node, the target representation vector obtained by the scheme has higher accuracy than a representation vector obtained in the prior art.
Description
technical field [0001] The present application relates to the field of computer technology, in particular, the present application relates to a network representation learning method, device, electronic equipment and readable storage medium. Background technique [0002] Network representation learning technology maps each node in the network to a fixed-length feature vector, and the dimension of this vector is much smaller than the number of nodes in the network, and this vector can preserve the network structure to a certain extent. That is to say, the closer two nodes are in the network structure, the closer the feature vectors of the two nodes are in the vector space. [0003] For large-scale networks, when performing network representation learning on them, the existing technology stores the representation vectors of nodes on the Parameter Server (Parameter Server) cluster, and when doing gradient descent (Gradient Descent), negatively sampled nodes and neighbors The n...
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 Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/24
CPCH04L41/0813H04L41/0823H04L41/14
Inventor 林文清
Owner TENCENT TECH (SHENZHEN) CO LTD