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

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

LAMDA: Aiding Visual Exploration of Atomic Displacements in Molecular Dynamics Simulations.

IEEE transactions on visualization and computer graphics·2026

Same author

Generative Graph Dictionary Learning.

Proceedings of machine learning research·2025

Same author

FEWSim: A Visual Analytic Framework for Exploring the Nexus of Food-Energy-Water Simulations.

IEEE computer graphics and applications·2025

Same author

Privacy-Preserving Graph Machine Learning from Data to Computation: A Survey.

SIGKDD explorations : newsletter of the Special Interest Group (SIG) on Knowledge Discovery & Data Mining·2025

Same author

Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders.

KDD : proceedings. International Conference on Knowledge Discovery & Data Mining·2025

Same author

ArieL: Adversarial Graph Contrastive Learning.

ACM transactions on knowledge discovery from data·2025

Same journal

Modeling the transmission dynamics of racism propagation with community resilience.

Computational social networks·2021

Same journal

A model for the co-evolution of dynamic social networks and infectious disease dynamics.

Computational social networks·2021

Same journal

Influence spreading model used to analyse social networks and detect sub-communities.

Computational social networks·2018

Same journal

Network partitioning algorithms as cooperative games.

Computational social networks·2018

Same journal

Social learning for resilient data fusion against data falsification attacks.

Computational social networks·2018

Same journal

Tracking online topics over time: understanding dynamic hashtag communities.

Computational social networks·2018

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 12, 2025

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

Graph convolutional networks: a comprehensive review.

Si Zhang¹, Hanghang Tong¹, Jiejun Xu²

¹University of Illinois Urbana-Champaign, Champaign, USA.

Computational Social Networks

|November 2, 2023

Summary

This summary is machine-generated.

This survey reviews graph convolutional networks (GCNs), a key deep learning method for graph representation learning. It categorizes GCNs by convolution type and application, highlighting challenges and future research directions in this emerging field.

Keywords:

Aggregation mechanism Deep learning Graph convolutional networks Graph representation learning Spatial methods Spectral methods

More Related Videos

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

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

Published on: June 13, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Related Experiment Videos

Last Updated: Jul 12, 2025

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

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

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

Published on: June 13, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Area of Science:

Machine Learning
Graph Theory
Computer Vision
Bioinformatics

Background:

Graphs are crucial for modeling complex relationships in diverse domains like social networks and bioinformatics.
Learning from graph-structured data is challenging due to data heterogeneity and complex connectivity patterns.
Representation learning offers a solution by mapping graph properties to low-dimensional Euclidean spaces.

Purpose of the Study:

To provide a comprehensive review of graph convolutional networks (GCNs), a prominent deep learning approach for graph representation learning.
To categorize existing GCN models based on their convolution mechanisms and application areas.
To identify current challenges and suggest future research directions in the field of GCNs.

Main Methods:

Categorization of GCN models based on two primary types of convolutions.
Detailed highlighting of specific GCN models within these categories.
Classification of GCNs according to their application domains.

Main Results:

Existing GCN models are grouped into distinct categories based on convolution techniques.
A taxonomy of GCNs is presented, organized by their application areas.
Key challenges and potential future research avenues are identified.

Conclusions:

Graph convolutional networks represent a significant advancement in deep learning for graph representation.
Understanding the landscape of GCNs through categorization aids in identifying research gaps.
Further research is needed to address open challenges and advance the capabilities of GCNs.