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

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...

Integration of Synaptic Events

Integration of Synaptic Events

Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...

Parallel Processing

Parallel Processing

The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...

You might also read

Related Articles

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

Sort by

Same author

APSevLM: Acute Pancreatitis Severity Language Model.

IEEE journal of biomedical and health informatics·2026

Same author

Chemical-Disease-Gene Association Prediction based on Pretraining-Prompt-Finetuning Heterogeneous Graph Neural Network for Drug Discovery.

IEEE journal of biomedical and health informatics·2026

Same author

Graph-Embedded Deep Generative Clustering for Single-Cell Multi-Omics Data Integration.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

A unified framework for sequential recommendation with gated differential amplified attention and repetition-exploration intent modeling.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Multiple interpretation ensemble distillation for graph neural networks.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

ID-Guided Multimodal experts with contrastive diffusion for sequential recommendation.

Neural networks : the official journal of the International Neural Network Society·2026

Search research articles

Related Experiment Video

Updated: Jun 16, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

MIGP: Metapath Integrated Graph Prompt Neural Network.

Pei-Yuan Lai¹, Qing-Yun Dai², Yi-Hong Lu³

¹School of Information Engineering, Guangdong University of Technology, Guangzhou, China; South China Technology Commercialization Center, Guangzhou, China.

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

|August 19, 2024

Summary

This summary is machine-generated.

This study introduces the Metapath Integrated Graph Prompt Neural Network (MIGP) to improve graph neural network (GNN) performance on small datasets by using learnable prompt vectors for enhanced node representations.

Keywords:

Graph neural network Graph prompt Heterogeneous graphs Metapath

More Related Videos

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Related Experiment Videos

Last Updated: Jun 16, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Area of Science:

Artificial Intelligence
Machine Learning
Graph Neural Networks

Background:

Graph neural networks (GNNs) using metapaths are widely used but face challenges with high training costs and poor generalization on small datasets.
Existing GNNs struggle with limited data, leading to diminished performance and generalization capacity.

Purpose of the Study:

To enhance node representations in GNNs for improved adaptability to downstream tasks, especially with limited data.
To introduce a novel approach, the Metapath Integrated Graph Prompt Neural Network (MIGP), to address GNN limitations in small-sample scenarios.

Main Methods:

Proposes the Metapath Integrated Graph Prompt Neural Network (MIGP) leveraging learnable prompt vectors for node representation enhancement.
Pretraining stage involves splitting metapaths and propagating information to update node representations.
Prompt-tuning stage uses fixed pretrained model parameters, independent basis vectors, and an attention mechanism to generate task-specific prompt vectors.

Main Results:

MIGP demonstrates superior performance across various downstream tasks on patent and public datasets (ACM, IMDB, DBLP).
The model effectively enhances GNN applicability and performance, particularly in small-sample dataset scenarios.
Introduction of three novel patent datasets for large-scale patent data analysis research.

Conclusions:

The proposed MIGP model effectively overcomes limitations of traditional GNNs on small datasets by enhancing generalization.
Learnable prompt vectors offer a promising direction for improving GNN adaptability and performance.
The publicly released datasets and source code will foster further research in graph representation learning and patent data analysis.