Unlock instant, AI-driven research and patent intelligence for your innovation.

Recommendation method based on clustering multi-entity graph neural network

A technology of neural network and recommendation method, which is applied in the field of recommendation based on clustered multi-entity graph neural network, can solve problems such as reducing training time, achieve the effect of improving prediction effect and generalization ability

Pending Publication Date: 2020-12-15
SUN YAT SEN UNIV
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this patent cannot achieve a good recommendation effect while greatly reducing training time

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
  • Recommendation method based on clustering multi-entity graph neural network
  • Recommendation method based on clustering multi-entity graph neural network
  • Recommendation method based on clustering multi-entity graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0036] In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0037] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings.

[0038] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0039] Such as figure 1 As shown, first: clustering. According to the graph clustering algorithm, the connectivity of the graph is analyzed, the graph is divided into multiple clusters, as many intra-cluster connections are retained as possible, and the connections between clusters are disconnected. When performing graph clustering, you can use a graph processing library such as metis. Such...

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

According to the recommendation method based on the clustering multi-entity graph neural network; a clustering algorithm is utilized, the graph neural network can be expanded to calculation of million-level nodes, and the training time complexity is only linearly increased rather than exponentially increased; the method can be applied to recommendation scenes (such as user-song list-song) under three entities or even more entities; different weight parameters can be configured for information transmission of nodes in two directions, and information transmission parameters used among differenttypes of nodes are different. Diversified information transmission weight configurations can improve the generalization ability of the network and improve the prediction effect.

Description

technical field [0001] The invention relates to the field of recommendation algorithms, and more specifically, to a recommendation method based on a clustered multi-entity graph neural network. Background technique [0002] Since the Internet wave in the United States and China, in order to recommend better products and content to users, improve user satisfaction, and increase the competitiveness of their own platforms, recommendation systems have been more and more widely used in various fields. In some industries, the recommendation system is even the core competitiveness of the company. For example, Taobao recommends products for users, and Douyin and Kuaishou recommend content for users. Excellent recommendation effects often make the company more competitive. The traditional recommendation system is content-based recommendation. By manually adding tags to products, and then analyzing the user's behavior trajectory, the final recommendation is given. The disadvantage of ...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 印鉴金子力刘威
Owner SUN YAT SEN UNIV