Search research articles

Related Concept Videos

Association Areas of the Cortex

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Predicting progression of Alzheimer's disease using blood-based multi-omics data.

Bioinformatics advances·2026

Same author

Combined inference of known and novel mutational signatures with ReDeNovo.

bioRxiv : the preprint server for biology·2026

Same author

From General-Purpose to Disease-Specific Features: Aligning LLM Embeddings on a Disease-Specific Biomedical Knowledge Graph for Drug Repurposing.

bioRxiv : the preprint server for biology·2026

Same author

BioLM-NET: an interpretable deep learning model combining prior biological knowledge and contextual LLM gene embeddings on multi-omics data to predict disease.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026

Same author

DyGraphTrans: A temporal graph representation learning framework for modeling disese progression from Electronic Health Records.

bioRxiv : the preprint server for biology·2026

Same author

MultiGEOmics: Graph-Based Integration of Multi-Omics via Biological Information Flows.

bioRxiv : the preprint server for biology·2026

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: Jun 6, 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

Fusing multiplex heterogeneous networks using graph attention-aware fusion networks.

Ziynet Nesibe Kesimoglu^1,2, Serdar Bozdag^3,4,5

¹Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA.

Scientific Reports

|November 24, 2024

Summary

This study introduces GRAF (Graph Attention-aware Fusion Networks), a novel framework for handling complex, multi-type networks in graph representation learning. GRAF effectively converts heterogeneous networks into homogeneous ones, improving performance on downstream machine learning tasks.

Keywords:

Attention aware network fusion Drug ADR prediction Graph neural networks

More Related Videos

Oncogenic Gene Fusion Detection Using Anchored Multiplex Polymerase Chain Reaction Followed by Next Generation Sequencing

Oncogenic Gene Fusion Detection Using Anchored Multiplex Polymerase Chain Reaction Followed by Next Generation Sequencing

Published on: July 5, 2019

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Related Experiment Videos

Last Updated: Jun 6, 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

Oncogenic Gene Fusion Detection Using Anchored Multiplex Polymerase Chain Reaction Followed by Next Generation Sequencing

Oncogenic Gene Fusion Detection Using Anchored Multiplex Polymerase Chain Reaction Followed by Next Generation Sequencing

Published on: July 5, 2019

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Area of Science:

Machine Learning
Network Science
Deep Learning

Background:

Graph Neural Networks (GNNs) are powerful for node and graph embeddings.
Real-world networks often feature multiple node and edge types, posing challenges for standard GNNs.
Heterogeneity and complex associations in networks require specialized approaches for effective representation learning.

Purpose of the Study:

To present GRAF (Graph Attention-aware Fusion Networks), a framework designed to convert multiplex heterogeneous networks into homogeneous ones.
To enhance suitability of complex networks for graph representation learning.
To improve node classification and similar downstream tasks on heterogeneous graph data.

Main Methods:

GRAF employs attention-based neighborhood aggregation, learning node-level and network layer-level attention weights.
A network fusion step integrates information by weighting edges based on learned attentions.
Edge elimination based on weights is followed by Graph Convolutional Networks (GCN) on the fused network, incorporating node features.

Main Results:

GRAF was applied to four diverse datasets, demonstrating its generalizability.
The framework achieved performance on par with or superior to baseline and state-of-the-art (SOTA) methods.
Attention weights provided interpretable insights into GRAF's findings.

Conclusions:

GRAF offers an effective solution for representation learning on multiplex heterogeneous networks.
The attention-based fusion mechanism allows for nuanced integration of network information.
The framework's performance and interpretability highlight its potential for various graph-structured data applications.