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

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...

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

Knowledge Transferred DRL-Based Adversary for Cyberattacks on Active Distribution Network Volt-Var Control Agents: When and How.

IEEE transactions on cybernetics·2026

Same author

Ancillary services in Great Britain during the COVID-19 lockdown: A glimpse of the carbon-free future.

Applied energy·2022

Same author

Heterogeneous network flow and Petri nets characterize multilayer complex networks.

Scientific reports·2022

Same author

On convergence for hybrid models of gene regulatory networks under polytopic uncertainties: a Lyapunov approach.

Journal of mathematical biology·2021

Same author

Scheduling of energy storage.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2021

Same author

A computational framework for a Lyapunov-enabled analysis of biochemical reaction networks.

PLoS computational biology·2020

Search research articles

Related Experiment Video

Updated: May 23, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Petri graph neural networks advance learning higher order multimodal complex interactions in graph structured data.

Alma Ademovic Tahirovic^1,2, David Angeli^3,4, Adnan Tahirovic^5,6

¹Department of Electrical and Electronic Engineering, Imperial College London, SW7 2AZ, London, UK. a.ademovic14@imperial.ac.uk.

Scientific Reports

|May 20, 2025

Summary

This study introduces Petri Graph Neural Networks (PGNNs) to model complex systems with higher-order, multimodal interactions. PGNNs enhance information flow and learning capabilities beyond traditional graph neural networks.

Keywords:

Heterogeneous network flow Higher-order complex networks Hypergraphs Multilayer networks Multimodal data Petri nets

More Related Videos

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

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

Related Experiment Videos

Last Updated: May 23, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

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

Area of Science:

Computer Science
Network Science
Machine Learning

Background:

Traditional graphs struggle with complex, multimodal, and higher-order real-world interactions.
Existing network models lack the capacity to represent diverse dependencies found in systems like brain connectivity or socio-economic networks.

Purpose of the Study:

To introduce a novel generalization of message passing for learning-based function approximation.
To present a new framework, multimodal heterogeneous network flow, for modeling information propagation under conservation constraints.
To introduce the Petri Graph Neural Network (PGNN) for learning over higher-order, multimodal structures.

Main Methods:

Defining a framework using Petri nets, which extend hypergraphs for concurrent, multimodal flow.
Developing the Petri Graph Neural Network (PGNN), a novel class of graph neural networks.
Generalizing message passing with flow conversion and concurrency within the PGNN framework.

Main Results:

PGNNs demonstrate enhanced expressive power, interpretability, and computational efficiency.
The framework successfully models information propagation across different semantic domains.
Superior performance was observed in real-world experiments, including stock market prediction.

Conclusions:

Petri Graph Neural Networks offer a powerful new approach for learning over complex, higher-order, and multimodal network structures.
This work transcends limitations of traditional graph neural networks and transformer-based algorithms.
PGNNs open new research directions in network science and machine learning.