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 Video

Updated: Mar 24, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.4K

Task Sensitive Feature Exploration and Learning for Multitask Graph Classification.

Shirui Pan, Jia Wu, Xingquan Zhu

    IEEE Transactions on Cybernetics
    |March 16, 2016
    PubMed
    Summary
    This summary is machine-generated.

    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

    Multilayered nucleotide organization reveals purifying selection and host-driven adaptation in CPV and FPV.

    BMC veterinary research·2026
    Same author

    Efficient Image Debiased Contrastive Clustering.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    Utility-Preserving Federated Graph Learning with Dual-Perspective Fairness.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    Efficient and selective Pd(II) capture from simulated electronic waste leachate by pyrimidine-based cellulose.

    International journal of biological macromolecules·2026
    Same author

    Federated learning: global insights from local plant data.

    Trends in plant science·2026
    Same author

    Mitochondrial Targeting of GSDMD-N and p-MLKL Drives PANoptosis in benzo[<i>a</i>]pyrene-Induced Hepatotoxicity.

    Journal of agricultural and food chemistry·2026
    Same journal

    An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models.

    IEEE transactions on cybernetics·2026
    Same journal

    A Quantum Self-Attention Neural Network Model on Quantum Circuits.

    IEEE transactions on cybernetics·2026
    Same journal

    Semi-Explicit Solution of Some Discrete-Time Higher-Order-Cost Mean-Field-Type Control.

    IEEE transactions on cybernetics·2026
    Same journal

    A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

    IEEE transactions on cybernetics·2026
    Same journal

    Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

    IEEE transactions on cybernetics·2026
    Same journal

    Digital Redesign-Based Interval State Estimation for Continuous Systems With Aperiodic Discrete Measurements.

    IEEE transactions on cybernetics·2026
    See all related articles

    This study introduces a novel multitask graph learning algorithm that discovers shared and unique subgraph features across tasks. This method enhances understanding of task relationships in graph classification for applications like brain analysis.

    Area of Science:

    • Machine Learning
    • Graph Theory
    • Data Mining

    Background:

    • Multitask learning (MTL) typically optimizes tasks with feature vectors, excluding structured data like graphs.
    • Existing MTL methods lack explicit task relationship analysis in feature spaces, limiting insights into shared vs. unique task elements.

    Purpose of the Study:

    • To develop a multitask graph learning framework for graph classification.
    • To explicitly capture and analyze task correlations and uniqueness within the feature space.

    Main Methods:

    • Proposed a task-sensitive feature exploration and learning algorithm for multitask graph classification.
    • Developed a paradigm to jointly discover discriminative subgraph features across tasks.
    • Iteratively optimized feature learning and multitask learning for global optimization, categorizing features as common, auxiliary, or task-specific.

    More Related Videos

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
    05:47

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

    Published on: June 13, 2025

    1.8K

    Related Experiment Videos

    Last Updated: Mar 24, 2026

    Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
    03:37

    Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

    Published on: March 1, 2024

    1.4K
    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
    05:47

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

    Published on: June 13, 2025

    1.8K

    Main Results:

    • Demonstrated performance on functional brain analysis and chemical compound categorization.
    • Successfully captured task correlations and uniqueness in the feature space.
    • Enabled explicit identification of shared and unique features between tasks.

    Conclusions:

    • The proposed algorithm effectively addresses limitations of existing MTL methods for graph data.
    • Provides a mechanism to explicitly understand feature sharing and distinctiveness across multiple learning tasks.
    • Offers valuable insights for complex graph classification problems in diverse scientific domains.