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 Concept Videos

Leaky Scanning02:28

Leaky Scanning

4.5K
During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA.  Marilyn Kozak discovered that the sequence RCCAUGG (where R...
4.5K
Chi-square Analysis02:46

Chi-square Analysis

29.1K
The chi-square test is a statistical hypothesis test. It is used to check whether there is a significant difference between an expected value and an observed value. In the context of genetics, it enables us to either accept or reject a hypothesis, based on how much the observed values deviate from the expected values.
The chi-square test was developed by Pearson in 1990.
The first step of performing a Chi-square analysis is to establish a null hypothesis, which assumes that there is no real...
29.1K
Conservative Forces01:14

Conservative Forces

10.5K
According to the law of conservation of energy, any transition between kinetic and potential energy conserves the total energy of the system. Hence, the work done by a conservative force is completely reversible. It is path independent, which means that we can start and stop at any two points in the transition, and the total energy of the system (kinetic plus potential energy at these points) will remain conserved. This is characteristic of a conservative force. Some important examples of...
10.5K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

7.3K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
7.3K
Interpreting R Charts01:22

Interpreting R Charts

506
R chart, or range chart, is a fundamental tool in statistical process control used to monitor the variability within a process. It complements the X-bar (x̄) chart by focusing on the range of the data, rather than individual values, providing a clear picture of the process dispersion over time.
An R chart plots the range of subsets of measurements collected from a process. Each point on the chart represents the range—defined as the difference between the maximum and minimum...
506
Understanding Deception01:14

Understanding Deception

266
Deception is a pervasive aspect of human communication. Empirical studies have shown that most individuals engage in some form of deceit on a daily basis, with approximately 20% of social exchanges involving deceptive elements. Lying follows a developmental trajectory, peaking during adolescence and declining with age, possibly due to the maturation of cognitive control and social accountability.Cognitive and Social Factors in Deception DetectionDespite its prevalence, accurately detecting...
266

You might also read

Related Articles

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

Sort by
Same author

Evaluation and correction methods for geometric errors of hydrostatic thrust bearings.

Scientific reports·2024
Same author

Predicting immunotherapy-related adverse events in late-stage non-small cell lung cancer with KARS G12C mutation treated with PD-1 inhibitors through combined assessment of LCP1 and ADPGK expression levels.

American journal of cancer research·2024
Same author

Enhancing genomic association studies in slash pine through close-range UAV-based morphological phenotyping.

Forestry research·2024
Same author

Engineering organoids-on-chips for drug testing and evaluation.

Metabolism: clinical and experimental·2024
Same author

Co-encapsulation of probiotic Lactiplantibacillus plantarum and polyphenol within novel polyvinyl alcohol/fucoidan electrospun nanofibers with improved viability and antioxidation.

International journal of biological macromolecules·2024
Same author

Protocol for analyzing invadopodia formation and gelatin degradation.

STAR protocols·2024

Related Experiment Video

Updated: May 7, 2026

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

3.8K

Revisiting low-homophily for graph-based fraud detection.

Tairan Huang1, Qiutong Li1, Cong Xu1

  • 1School of Computer Science and Engineering, Central South University, Changsha, China.

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2025
PubMed
Summary

This study introduces HeteGAD, a novel graph neural network (GNN) framework for fraud detection. HeteGAD effectively balances homophily and heterophily, outperforming existing methods on real-world datasets.

Keywords:
Fraud detectionGraph neural networksLabel imbalanceLow homophily

More Related Videos

Evaluation of a Point-of-Care Testing Analyzer for Measuring Peripheral Blood Leukocytes
05:58

Evaluation of a Point-of-Care Testing Analyzer for Measuring Peripheral Blood Leukocytes

Published on: March 22, 2022

3.8K
Dot Blot Assay for Detecting Global N6-Methyladenosine RNA Modification Levels
08:40

Dot Blot Assay for Detecting Global N6-Methyladenosine RNA Modification Levels

Published on: February 6, 2026

260

Related Experiment Videos

Last Updated: May 7, 2026

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

3.8K
Evaluation of a Point-of-Care Testing Analyzer for Measuring Peripheral Blood Leukocytes
05:58

Evaluation of a Point-of-Care Testing Analyzer for Measuring Peripheral Blood Leukocytes

Published on: March 22, 2022

3.8K
Dot Blot Assay for Detecting Global N6-Methyladenosine RNA Modification Levels
08:40

Dot Blot Assay for Detecting Global N6-Methyladenosine RNA Modification Levels

Published on: February 6, 2026

260

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Data Mining

Background:

  • Online fraud presents a significant threat, necessitating advanced detection methods.
  • Graph Neural Networks (GNNs) leverage graph structure for fraud detection but struggle with the heterophilous connections typical of fraudsters.
  • Existing GNNs often fail to effectively utilize heterophily, limiting their performance in fraud detection.

Purpose of the Study:

  • To develop a novel framework, HeteGAD, that addresses the limitations of conventional GNNs in fraud detection by effectively handling both homophilous and heterophilous graph structures.
  • To improve the accuracy and robustness of fraud detection systems by explicitly modeling the interplay between homophily and heterophily.

Main Methods:

  • Proposed HeteGAD, an integrated framework with two core strategies: Heterophily-aware Aggregation and Homophily-aware Aggregation.
  • The Heterophily-aware Aggregation Strategy enhances feature disparity in heterophilous neighbors and increases inter-class segregation.
  • The Homophily-aware Aggregation Strategy captures global homophilous information and augments representation similarity for same-labeled nodes. Incorporated inter-relational attention mechanisms refine multi-relation modeling.

Main Results:

  • HeteGAD demonstrated superior performance in fraud detection tasks compared to 11 state-of-the-art baseline methods.
  • Experiments on two real-world datasets validated the effectiveness of the proposed framework in balancing homophily and heterophily.
  • The framework successfully shrinks intra-class distances and increases inter-class segregation, crucial for distinguishing fraudsters.

Conclusions:

  • HeteGAD offers a significant advancement in graph-based fraud detection by effectively integrating homophilous and heterophilous information.
  • The proposed approach provides a more robust and accurate solution for identifying fraudulent activities in complex network structures.
  • This work highlights the importance of considering both homophily and heterophily for improved GNN performance in real-world fraud detection scenarios.