Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Neuroplasticity01:01

Neuroplasticity

262
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
262
Woodward–Hoffmann Selection Rules and Microscopic Reversibility01:34

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

3.0K
Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...
3.0K
Associative Learning01:27

Associative Learning

273
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
273

You might also read

Related Articles

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

Sort by
Same author

Hyaluronic acid-modified nanoparticles for chemo/sonodynamic therapy: Maximizing antitumor efficacy through the induction of ferroptosis and apoptosis.

International journal of biological macromolecules·2026
Same author

Metabolic-inflammatory axis linking diabetes and sarcopenia: cross-population evidence and explainable ai-based risk modeling.

Acta diabetologica·2026
Same author

A wearable IMU-based framework for daily physical activity recognition and energy expenditure level classification in university students.

Frontiers in public health·2026
Same author

A Copper-Catalyzed Approach to Access (Het)Aryl/Alkenyl Selenoglycosides Employing Electrophilic Glycosyl Selenosulfonates.

Organic letters·2026
Same author

Cross-model diffusion: Mitigating hallucination in large language models for rumor detection.

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

First-principles study of the electronic structure and optical properties of Ce and C Co-doped AlN.

Journal of molecular modeling·2026
Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

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

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

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

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

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

Anchor-based disentanglement framework for incremental multi-view clustering.

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

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

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

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: May 22, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

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

Published on: February 15, 2017

6.9K

Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction.

Weihong Lin1, Zhaoliang Chen2, Yuhong Chen1

  • 1College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China; Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou 350108, China.

Neural Networks : the Official Journal of the International Neural Network Society
|March 13, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction (HGNN-AR²) to improve heterogeneous graph learning. The model enhances node embeddings by reconstructing relations, addressing limitations of meta-path based methods.

Keywords:
Graph augmentationGraph learningGraph neural networksHeterogeneous information networksSemi-supervised classification

More Related Videos

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

967
Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

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

Published on: December 7, 2021

2.1K

Related Experiment Videos

Last Updated: May 22, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

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

Published on: February 15, 2017

6.9K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

967
Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

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

Published on: December 7, 2021

2.1K

Area of Science:

  • Graph Representation Learning
  • Machine Learning
  • Data Mining

Background:

  • Real-world graphs possess complex topological structures with diverse nodes and relation types, presenting challenges for traditional graph learning.
  • Heterogeneous graph learning methods, particularly those using meta-paths, aim to capture composite relations but often overlook intra-category connections, impacting node embedding quality.
  • Existing meta-path based approaches may create connections between different node categories while neglecting same-category relations, thus diminishing the effectiveness of node representations.

Purpose of the Study:

  • To propose a novel Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction (HGNN-AR²) to address the limitations of existing meta-path based heterogeneous graph learning methods.
  • To adaptively adjust relations within heterogeneous graphs to alleviate connection deficiencies and mitigate heteromorphic issues.
  • To enhance the quality of node embeddings by uncovering and incorporating unique, pertinent latent relations derived from multiple meta-paths.

Main Methods:

  • The HGNN-AR² model leverages distinct connections derived from multiple meta-paths to capture complex graph structures.
  • It examines homomorphic correlations of latent features across different meta-paths to reshape cross-node connections.
  • Relation reconstruction is employed to unveil unique connections specific to each meta-path, which are then integrated into graph convolutional networks for enhanced representations.

Main Results:

  • The proposed HGNN-AR² model demonstrates superior performance on various benchmark heterogeneous graph datasets.
  • Adaptive relation reconstruction effectively addresses connection deficiencies and heteromorphic issues inherent in heterogeneous graphs.
  • The model achieves more comprehensive node representations by incorporating reconstructed latent relations.

Conclusions:

  • HGNN-AR² offers a significant advancement in heterogeneous graph learning by effectively reconstructing relations to improve node embeddings.
  • The method provides a robust solution for capturing both inter- and intra-category relations in complex graph structures.
  • The superior performance validates the efficacy of adaptive relation reconstruction for enhancing heterogeneous graph analysis.