Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

End Point Prediction: Gran Plot

End Point Prediction: Gran Plot

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...

Types of Skewness

Types of Skewness

If the frequency distribution of a data set is more inclined towards smaller or larger values, the distribution is said to be skewed. If data values are skewed to the right, then the distribution is called positively skewed. Conversely, if the plot is skewed to the left, the distribution is called negatively skewed.
For instance, in the middle of a pandemic, the geographical distribution of vaccine coverage may be positively skewed towards populations in the global north countries. However,...

Correlations

Correlations

Correlation means that there is a relationship between two or more variables (such as ice cream consumption and crime), but this relationship does not necessarily imply cause and effect. When two variables are correlated, it simply means that as one variable changes, so does the other. We can measure correlation by calculating a statistic known as a correlation coefficient. A correlation coefficient is a number from -1 to +1 that indicates the strength and direction of the relationship between...

Hypothesis: Accept or Fail to Reject?

Hypothesis: Accept or Fail to Reject?

The outcome of any hypothesis testing leads to rejecting or not rejecting the null hypothesis. This decision is taken based on the analysis of the data, an appropriate test statistic, an appropriate confidence level, the critical values, and P-values. However, when the evidence suggests that the null hypothesis cannot be rejected, is it right to say, 'Accept' the null hypothesis?
There are two ways to indicate that the null hypothesis is not rejected. 'Accept' the null...

You might also read

Related Articles

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

Sort by

Same author

Coherent transformation of metal halide perovskites.

Nature communications·2026

Same author

Unraveling the Distinct Roles of Al and Ca in Microstructure Evolution and Tensile Response of Extruded Mg-Al-Ca Alloys.

Materials (Basel, Switzerland)·2026

Same author

Forced changes in a Tibetan lake ecosystem over the past millennium.

Nature communications·2026

Same author

An acoustically transmissive electrochemical vector hydrophone with horn-driven velocity amplification.

Microsystems & nanoengineering·2026

Same author

Clear Aligner Attachments: A Scoping Review.

Orthodontics & craniofacial research·2026

Same author

Generalizable self-supervised learning for imaging flow cytometry on multi-dataset leukocyte differential.

Microsystems & nanoengineering·2026

Search research articles

Related Experiment Video

Updated: Jun 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Hypergraph contrastive attention networks for hyperedge prediction with negative samples evaluation.

Junbo Wang¹, Jianrui Chen², Zhihui Wang¹

¹School of Computer Science, Shaanxi Normal University, Xi'an, China.

Neural Networks : the Official Journal of the International Neural Network Society

|October 24, 2024

Summary

This study introduces the Hypergraph Contrastive Attention Network (HCAN) for hyperedge prediction, improving relation discovery in hypergraphs. HCAN enhances feature learning and addresses negative sampling challenges for more reliable predictions.

Keywords:

Contrastive learning Hyperedge prediction Hypergraph attention networks Negative sampling evaluation Order attention mechanism

More Related Videos

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

Related Experiment Videos

Last Updated: Jun 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

Area of Science:

Computer Science
Graph Theory
Machine Learning

Background:

Hyperedge prediction identifies future or undiscovered relations among multiple nodes in hypergraphs.
Traditional methods treat hyperedge prediction as a classification task, facing challenges in hyperedge feature learning and negative sample generation.

Purpose of the Study:

To propose a novel Hypergraph Contrastive Attention Network (HCAN) for improved hyperedge prediction.
To address limitations in measuring node influence on hyperedges and the impact of negative samples in classification.

Main Methods:

HCAN employs an order propagation attention mechanism, inspired by brain organization, to capture hyperedge influences of varying orders.
A contrastive mechanism is utilized to enhance attention reliability.
A negative sample generator creates three distinct types of negative samples to evaluate their impact.

Main Results:

The study evaluates the influence of different negative samples on model performance.
HCAN demonstrates effectiveness in hyperedge prediction, outperforming 12 baseline methods across 9 datasets.
Analysis reveals issues with traditional binary classification modeling for hyperedge prediction.

Conclusions:

HCAN offers a robust solution for hyperedge prediction by effectively learning hypergraph features and handling negative sampling.
The proposed model shows significant improvements in predicting future or undiscovered relationships in hypergraphs.
Open-source implementation is available for reproducibility and further research.