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

Development and Validation of a Crotonylation-Related Prognostic Risk Model for Cholangiocarcinoma Based on Integrative Transcriptome Analysis.

Digestive diseases and sciences·2026

Same author

Privacy-Preserving Virtual Contrast-enhanced MRI for Nasopharyngeal Carcinoma: A Multi-center Study.

International journal of radiation oncology, biology, physics·2026

Same author

Operationalizing Digital Health Equity in Artificial Intelligence-Enabled Patient Decision Aids for Older Adults: Mixed Methods Study.

Journal of medical Internet research·2026

Same author

Deep learning-enabled self-powered bimodal flexible sensor for intelligent access control.

Nanotechnology·2026

Same author

Tianhuang Formula and its active ingredient GsRg1 ameliorate central insulin resistance and oxidative stress by enhancing hypothalamic autophagy.

Journal of ethnopharmacology·2026

Same author

Optimization of a Wedge Shaped T-Type Magnetic Flux Concentrator for High-Sensitivity TMR Sensors.

Micromachines·2026

Search research articles

Related Experiment Video

Updated: Jun 21, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

AutoAMS: Automated attention-based multi-modal graph learning architecture search.

Raeed Al-Sabri¹, Jianliang Gao¹, Jiamin Chen¹

¹School of Computer Science and Engineering, Central South University, Changsha, 410083, Hunan, China.

Neural Networks : the Official Journal of the International Neural Network Society

|July 14, 2024

Summary

This summary is machine-generated.

Automated attention-based multi-modal graph learning architecture search (AutoAMS) framework automates the design of high-performance multi-modal graph learning architectures. This approach overcomes limitations of manual design and existing graph neural architecture search methods.

Keywords:

Attention representation Graph neural architecture search Graph neural network Multi-modal learning

More Related Videos

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

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

Related Experiment Videos

Last Updated: Jun 21, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

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

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

Area of Science:

Artificial Intelligence
Machine Learning
Graph Neural Networks

Background:

Multi-modal attention mechanisms are effective in multi-modal graph learning but rely on manual design.
Existing graph neural architecture search (GNAS) methods are not directly applicable to multi-modal graph learning due to limited search spaces and objectives.
Manual design of attention-based multi-modal graph learning (AMGL) architectures is labor-intensive and requires expert knowledge.

Purpose of the Study:

To propose an automated framework, AutoAMS, for designing optimal AMGL architectures.
To address the challenges of manual design and limitations of existing GNAS methods in the multi-modal context.
To enable automatic search for effective multi-modal attention representations and other AMGL components.

Main Methods:

Developed an automated attention-based multi-modal graph learning architecture search (AutoAMS) framework.
Designed an attention-based multi-modal (AM) search space with four sub-spaces for joint optimization.
Introduced a novel search objective combining unsupervised multi-modal reconstruction loss and task-specific loss.

Main Results:

The AutoAMS framework successfully automates the design of AMGL architectures.
The proposed AM search space effectively supports the automatic search of multi-modal attention and other components.
The novel search objective captures global features and multi-modal interactions.
Experimental results demonstrate AutoAMS's capability in designing high-performance AMGL architectures for multi-modal tasks.

Conclusions:

AutoAMS provides an effective automated solution for designing AMGL architectures.
The framework overcomes the limitations of manual design and existing GNAS methods.
AutoAMS facilitates the development of high-performance multi-modal learning systems.