Information cascade prediction method based on GAT-LSTM

A technology of information cascading and prediction method, applied in prediction, neural learning method, data processing application, etc., to achieve the effect of strong accuracy, reduced training time, and improved prediction accuracy

Pending Publication Date: 2022-07-05
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

While network structure and cascaded time series can be easily obtained independent...

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
  • Information cascade prediction method based on GAT-LSTM
  • Information cascade prediction method based on GAT-LSTM
  • Information cascade prediction method based on GAT-LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to explain the technology and advantages of the present invention in more detail and clearly, the embodiments and effects of the present invention will be described in further detail below with reference to the accompanying drawings.

[0026] The information cascade prediction method based on GAT-LSTM, its overall structure diagram is as follows figure 1 First, the public information cascade data set is preprocessed, the form of cascade snapshot is defined, and node features are learned through a single-layer four-head GAT (graph attention network). These node features are fed into a dynamic routing algorithm for node aggregation, resulting in a vector representation of cascaded snapshots. Then, the time information hidden in the cascaded snapshots is combined and sent to a single-layer LSTM (Long Short-Term Memory Recurrent Neural Network), so that the model can fully learn the structural information and time information. The resulting vector is then fed into...

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

The invention discloses a prediction method for a forwarding cascade scale. According to the method, a GAT (graph attention network), a dynamic route and an LSTM (long short-term memory recurrent neural network) are combined into a new model for predicting the information cascade scale. The method comprises the following steps: preprocessing data; the graph attention network extracts node features; cascading snapshots are divided; dynamically routing and aggregating node information; the LSTM extracts time information; carrying out final prediction by using an MLP (Multilayer Perceptron); and testing the model. The method can be applied to the field of popularity prediction. The invention provides a new feature extraction method for the field, solves the problems of low prediction efficiency, low information utilization rate after multiple models are combined and the like in the field, and meets the requirements of rapid prediction and capture of hot events.

Description

technical field [0001] The invention belongs to the field of popularity prediction, and further relates to an information cascade prediction method based on GAT-LSTM. Background technique [0002] The research on news popularity prediction in online social networks aims to predict and identify future popular news from massive information in advance, and help people to get rid of the dilemma of information overload. However, due to the openness of social networks and the strong uncertainty of cascading propagation effects in social networks, it is an extremely difficult and challenging task to accurately predict the future popularity of messages. [0003] At present, news popularity prediction methods are mainly divided into two categories. One is the feature-based extraction method. This method usually analyzes the content of text, the amount of likes, the amount of forwarding, the gender of the original user, the registration time, and the degree of activity. Feature extra...

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): G06Q10/04G06Q10/06G06Q50/00G06N3/08
CPCG06Q10/04G06Q10/06393G06Q50/01G06N3/08
Inventor 李刚孟涛周鸣乐韩德隆李敏李旺
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap