Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Link Prediction in Heterogeneous Information Networks: Improved Hypergraph Convolution with Adaptive Soft Voting.

Sheng Zhang1, Yuyuan Huang1, Ziqiang Luo1

  • 1School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China.

Entropy (Basel, Switzerland)
|February 27, 2026
PubMed
Summary

Related Concept Videos

End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

1.3K
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
1.3K
Prediction Intervals01:03

Prediction Intervals

3.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
3.5K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Epicardial ganglionated plexi ablation increases the inducibility of ventricular tachyarrhythmias in a canine postmyocardial infarction model.

Journal of cardiovascular electrophysiology·2019
Same author

Value of <sup>18</sup>F-FDG PET/CT in the diagnosis of portal vein tumor thrombus in patients with hepatocellular carcinoma.

Abdominal radiology (New York)·2019
Same author

Accurate Determination of Trace Molybdenum in Drinking Water by Isotope Dilution Inductively Coupled Plasma Mass Spectrometry.

Analytical sciences : the international journal of the Japan Society for Analytical Chemistry·2019
Same author

Using clinical genomic sequencing to guide personalized cancer therapy in China.

Personalized medicine·2019
Same author

Value of High-Resolution DWI in Combination With Texture Analysis for the Evaluation of Tumor Response After Preoperative Chemoradiotherapy for Locally Advanced Rectal Cancer.

AJR. American journal of roentgenology·2019
Same author

Ingrowth of Nociceptive Receptors into Diseased Cervical Intervertebral Disc Is Associated with Discogenic Neck Pain.

Pain medicine (Malden, Mass.)·2019

This study introduces VE-HGCN, a novel model for link prediction in heterogeneous information networks (HINs). It enhances accuracy by fusing hypergraph convolution with a soft-voting ensemble strategy for complex network analysis.

Area of Science:

  • Computer Science
  • Network Analysis
  • Machine Learning

Background:

  • Complex real-world systems are modeled as heterogeneous information networks (HINs).
  • Traditional link prediction methods struggle with high-order structures and semantics in HINs.
  • Existing hypergraph models may dilute important associations by homogenizing high-order information.

Purpose of the Study:

  • To propose the VE-HGCN model for improved link prediction in HINs.
  • To address limitations of traditional and existing hypergraph-based methods.
  • To effectively utilize high-order information in complex heterogeneous network analysis.

Main Methods:

  • Constructing multiple heterogeneous hypergraphs from HINs using frequent subgraph pattern extraction.
  • Applying hypergraph convolution for effective node representation learning.
Keywords:
heterogeneous information networkshypergraph convolutional neural networklink predictionsoft-voting ensemble strategy

Related Experiment Videos

  • Employing a soft-voting ensemble strategy to fuse multi-model prediction results.

    • Main Results:

    • The VE-HGCN model demonstrated superior performance compared to seven mainstream baseline models.
    • Experiments were conducted on four public HIN datasets, validating the model's effectiveness.
    • The proposed method significantly outperforms existing approaches in link prediction accuracy.

    Conclusions:

    • VE-HGCN offers a new perspective for link prediction in HINs.
    • The model exhibits good generality and practicality for complex network analysis.
    • This study provides a feasible reference for utilizing high-order information in HINs.