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

Search research articles

Related Experiment Video

Updated: Jan 3, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

GrAMME: Semisupervised Learning Using Multilayered Graph Attention Models.

Uday Shankar Shanthamallu, Jayaraman J Thiagarajan, Huan Song

IEEE Transactions on Neural Networks and Learning Systems

|November 15, 2019

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

Radical-omics reveals the hydrogen-abstraction pathway of isoprene oxidation.

Nature communications·2026

Same author

From Foundation to Intelligence Integration: The Synergistic Associations of ICT and AI Support with Pre-Service Teachers' TPACK Development.

Behavioral sciences (Basel, Switzerland)·2026

Same author

Genomic structural equation modelling of 12 cancers identifies a latent pan-cancer susceptibility factor and shared determinants of carcinogenesis.

EBioMedicine·2026

Same author

Corrigendum to "Shengxian decoction mitigate bleomycin-induced pulmonary fibrosis in mice via MerTK mediated macrophage efferocytosis" [J. Ethnopharmacol. 365 (2026) 121583].

Journal of ethnopharmacology·2026

Same author

Cohort profile: transformative research on equity and social determinants to uplift resilience and empower LGBTQ+ health in China (TREASURE).

European journal of epidemiology·2026

Same author

Adverse childhood experiences and risk of living with HIV among lesbian, gay, bisexual, transgender, and queer/questioning (LGBTQ+) people: a cross-sectional study.

The Lancet regional health. Western Pacific·2026

Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026

Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026

Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

See all related articles

This study introduces novel graph neural network architectures, GrAMME-SG and GrAMME-Fusion, for enhanced node classification in complex multilayered graphs. These methods effectively leverage random node attributes and attention mechanisms for superior performance in semisupervised learning tasks.

Area of Science:

Graph Neural Networks
Machine Learning
Data Science

Background:

Modern data analysis increasingly involves complex multiview information sources.
Multilayered graphs offer richer representations than single graphs but pose challenges for existing solutions.
Classical problems like node classification require novel approaches for multilayered graph scenarios.

Purpose of the Study:

To develop effective semisupervised learning methods for multilayered graphs.
To propose novel graph neural network architectures for multilayered graph embeddings.
To demonstrate the efficacy of attention models and random node attributes for feature learning.

Main Methods:

Proposed two novel architectures: GrAMME-SG and GrAMME-Fusion.

More Related Videos

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

Related Experiment Videos

Last Updated: Jan 3, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

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

Utilized attention models for effective feature learning in multilayered graphs.

Exploited interlayer dependencies for building multilayered graph embeddings using random node attributes.

Main Results:

Achieved significant performance improvements over state-of-the-art network embedding strategies.
Demonstrated the effectiveness of GrAMME-SG and GrAMME-Fusion on benchmark datasets.
Showcased that simple random features are effective, even without explicit node attributes.

Conclusions:

The proposed GrAMME models offer superior performance for node classification in multilayered graphs.
Attention-based feature learning with random attributes is a viable and effective strategy.
Novel solutions are crucial for addressing complex problems in multilayered graph analysis.