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

Investigation of Temperature-Field Evolution and Microstructural Response in Bituminous Waterproofing Membranes Under Low-Temperature Flexibility Testing Conditions.

Polymers·2026
Same author

Retraction notice to "Safe use of liver grafts from hepatitis B surface antigen positive donors in liver transplantation" [J Hepatol 61 (2014) 809-815].

Journal of hepatology·2026
Same author

Evolving Strategies for Previously Drugged Therapeutic Targets: Medicinal Chemistry Insights from Paradigmatic Cases.

Journal of medicinal chemistry·2026
Same author

Meckel's diverticulum complicated by a congenital intestinal adhesive band: a case report and literature review.

Frontiers in pediatrics·2026
Same author

Vesicovaginal reflux: a case report and literature overview.

Frontiers in pediatrics·2026
Same author

A highly feasible simulation model based on nipple-preserving pork portions for practicing superficial mass resection.

BMC surgery·2026

Related Experiment Video

Updated: Jun 14, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Graph Neural Networks With Adaptive Confidence Discrimination.

Yanbei Liu, Lu Yu, Shichuan Zhao

    IEEE Transactions on Neural Networks and Learning Systems
    |September 4, 2024
    PubMed
    Summary

    This study introduces Adaptive Confidence Discrimination Graph Neural Networks (ACDGNN) to improve semisupervised node classification by better utilizing unlabeled data. ACDGNN achieves significant accuracy gains, outperforming existing methods.

    More Related Videos

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

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

    Published on: December 15, 2023

    492
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    6.9K

    Related Experiment Videos

    Last Updated: Jun 14, 2025

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.0K
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

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

    Published on: December 15, 2023

    492
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    6.9K

    Area of Science:

    • Machine Learning
    • Graph Neural Networks
    • Artificial Intelligence

    Background:

    • Graph Neural Networks (GNNs) excel in semisupervised node classification but underutilize unlabeled data.
    • Existing pseudolabeling methods in semisupervised learning (SSL) suffer from fixed thresholds and low data utilization, causing class imbalance.

    Purpose of the Study:

    • To propose GNNs with Adaptive Confidence Discrimination (ACDGNN) for enhanced semisupervised node classification.
    • To fully leverage unlabeled samples in semisupervised learning through a novel approach.

    Main Methods:

    • Developed an adaptive confidence discrimination module to dynamically threshold unlabeled nodes.
    • Implemented distinct strategies: high-confidence nodes expand the label set, low-confidence nodes use contrastive learning for discriminative features.

    Main Results:

    • ACDGNN achieved significant accuracy improvements over state-of-the-art methods.
    • Demonstrated an average accuracy gain of 2.0% across datasets, with a notable 5.7% improvement on the Flickr dataset.

    Conclusions:

    • ACDGNN effectively utilizes unlabeled data for semisupervised node classification.
    • The proposed adaptive strategy enhances model performance and data utilization compared to conventional methods.