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

You might also read

Related Articles

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

Sort by
Same author

Loganin Alleviates CCl<sub>4</sub>-Induced Acute Liver Injury by Promoting Mitophagy and Inhibiting NLRP3 Inflammasome.

Chinese journal of integrative medicine·2026
Same author

Histologically validated diffusion MRI signatures of neuroinflammation and neurodegeneration in Alzheimer disease.

medRxiv : the preprint server for health sciences·2026
Same author

HJURP upregulation, driven by transcription factor NFYA, promotes endometrial carcinoma progression via regulating RASSF8 ubiquitination.

Functional & integrative genomics·2026
Same author

Reassessing the role of antiphospholipid antibodies in placental-mediated adverse pregnancy outcomes in systemic lupus erythematosus: A retrospective cohort study.

International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics·2026
Same author

Organic Chemistry as a Catalyst for AI Innovation: Challenges, Methods, and Emerging Paradigms.

Chemical reviews·2026
Same author

Machine learning-based mri radiomics for predicting bevacizumab response in peritumoral brain edema of glioblastoma.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

Related Experiment Video

Updated: Oct 22, 2025

Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products
11:13

Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products

Published on: March 12, 2020

11.2K

A Synergistic Approach for Graph Anomaly Detection With Pattern Mining and Feature Learning.

Tong Zhao, Tianwen Jiang, Neil Shah

    IEEE Transactions on Neural Networks and Learning Systems
    |August 30, 2021
    PubMed
    Summary

    This study introduces a novel synergistic approach for graph anomaly detection, combining global pattern mining with local feature learning using graph neural networks (GNNs). The method significantly improves anomaly detection accuracy on real-world datasets.

    More Related Videos

    Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations
    08:03

    Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations

    Published on: December 7, 2021

    2.5K
    Cross-Modal Multivariate Pattern Analysis
    13:51

    Cross-Modal Multivariate Pattern Analysis

    Published on: November 9, 2011

    20.1K

    Related Experiment Videos

    Last Updated: Oct 22, 2025

    Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products
    11:13

    Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products

    Published on: March 12, 2020

    11.2K
    Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations
    08:03

    Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations

    Published on: December 7, 2021

    2.5K
    Cross-Modal Multivariate Pattern Analysis
    13:51

    Cross-Modal Multivariate Pattern Analysis

    Published on: November 9, 2011

    20.1K

    Area of Science:

    • Graph Analytics
    • Machine Learning
    • Data Mining

    Background:

    • Graph anomaly detection commonly employs either global pattern mining or local feature learning via graph neural networks (GNNs).
    • Existing methods often fail to integrate both global structural patterns and local neighborhood information for comprehensive anomaly detection.
    • A gap exists in synergistic approaches that leverage global context to guide local information aggregation in GNNs.

    Purpose of the Study:

    • To propose a novel synergistic approach for graph anomaly detection that integrates pattern mining with GNN-based feature learning.
    • To enhance the capability of GNNs in capturing global graph patterns by incorporating insights from pattern mining.
    • To develop a new loss function that enables pattern mining algorithms to supervise GNN training for improved anomaly detection.

    Main Methods:

    • A GNN encoder is utilized for feature aggregation, learning node representations from local neighborhoods.
    • Pattern mining algorithms are employed to guide the GNN's aggregation process through a novel, supervisory loss function.
    • The synergistic approach is evaluated across various GNN architectures and pattern mining techniques.

    Main Results:

    • Theoretical analysis confirms the effectiveness of the proposed loss function in guiding GNNs.
    • Empirical analysis demonstrates the superior performance of the synergistic approach compared to existing methods.
    • Experiments on real-world datasets show significant improvements in graph anomaly detection accuracy.

    Conclusions:

    • The proposed synergistic approach effectively combines global pattern mining and local GNN feature learning for superior graph anomaly detection.
    • Integrating pattern mining insights into GNN training via a novel loss function enhances the detection of anomalies.
    • This hybrid methodology offers a promising direction for advancing the field of graph anomaly detection.