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...

You might also read

Related Articles

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

Sort by

Same author

Prognostic RNA-splicing archetypes in breast cancer identified by extended pre-training of histopathology foundation models.

Nature communications·2026

Same author

CARS_SPA optimized UV-Vis spectroscopy for rapid and robust COD prediction in water samples.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Same author

Licochalcone a Disrupted Mitochondrial Function to Promote Cuproptosis in Glioblastoma Through Regulating RAS/MAPK Pathway.

Applied biochemistry and biotechnology·2026

Same author

Bidirectional effect modification between diurnal temperature range and particulate matter on acute myocardial infarction risk.

iScience·2026

Same author

6H2L, a novel derivative of bifendate, dually suppresses glycolysis and glutaminolysis in hepatocellular carcinoma via inhibiting YAP stability.

Chemico-biological interactions·2026

Same author

Future cardiovascular events prediction from invasive coronary angiography: A graph representation learning perspective.

Medical image analysis·2026

Search research articles

Related Experiment Video

Updated: Nov 10, 2025

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

iPool-Information-Based Pooling in Hierarchical Graph Neural Networks.

Xing Gao, Wenrui Dai, Chenglin Li

IEEE Transactions on Neural Networks and Learning Systems

|March 31, 2021

Summary

Researchers developed iPool, a novel parameter-free graph pooling method. This approach effectively retains essential features in network data, improving graph classification performance.

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Related Experiment Videos

Last Updated: Nov 10, 2025

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

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Area of Science:

Graph Neural Networks
Data Science
Network Analysis

Background:

Graph data analysis is crucial in data science.
Existing graph neural networks primarily focus on convolution operators.
Graph pooling, vital for hierarchical representations, is underexplored.

Purpose of the Study:

Introduce iPool, a parameter-free pooling operator for arbitrary graphs.
Develop a method to retain the most informative features in graph data.
Enhance graph representation learning for improved classification.

Main Methods:

Propose iPool, a parameter-free pooling operator.
Define an information-content criterion for node selection based on neighborhood conditional entropy.
Construct coarsened graphs using the proposed node selection strategy.

Main Results:

iPool effectively retains informative graph features.
The method generates isomorphism-invariant representations for networked data.
Achieved superior or competitive performance on graph classification benchmarks.

Conclusions:

iPool offers a novel and effective approach to graph pooling.
The parameter-free nature and information-centric criterion enhance graph representation.
The method demonstrates broad applicability across various graph topologies and datasets.