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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

137
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
137
Associative Learning01:27

Associative Learning

484
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...
484
Observational Learning01:12

Observational Learning

250
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
250
Cognitive Learning01:21

Cognitive Learning

464
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
464
Vector Algebra: Graphical Method01:10

Vector Algebra: Graphical Method

12.6K
Vectors can be multiplied by scalars, added to other vectors, or subtracted from other vectors. The vector sum of two (or more) vectors is called the resultant vector or, for short, the resultant.
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
12.6K
Introduction to Learning01:18

Introduction to Learning

493
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
493

You might also read

Related Articles

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

Sort by
Same author

Dual-Carbon Synergistic Strategy Enabling SbPO<sub>4</sub>@MFC/rGO Composites With Hierarchical Conduction Network for High-Performance Sodium-Ion Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

MVR-DTI: A Multimodal Molecular Visual Representation Learning for Drug-Target Interaction Prediction.

Journal of chemical information and modeling·2026
Same author

Attention-Guided Multi-View Contrastive Learning for Predicting Sparse Drug-Gene Associations.

Interdisciplinary sciences, computational life sciences·2026
Same author

Inhibition of PRMT5 reduces angiogenesis in a corneal neovascularization model by blocking NLRP3-mediated pyroptosis.

Clinical epigenetics·2026
Same author

Elevated plasma klotho levels attenuate Alzheimer's disease pathologies and cognitive decline in APOE ε4 carriers.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Influencing Factors of New-Onset Atrial Fibrillation in Sepsis Patients and Construction of a Nomogram Prediction Model: Based on LASSO Regression.

International journal of general medicine·2026

Related Experiment Video

Updated: Aug 6, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

406

Dual adaptive learning multi-task multi-view for graph network representation learning.

Beibei Han1, Yingmei Wei1, Qingyong Wang1

  • 1College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, PR China.

Neural Networks : the Official Journal of the International Neural Network Society
|March 18, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces M²agl, a novel graph network representation learning model that effectively integrates multi-task and multi-view information. M²agl enhances graph analysis by adaptively balancing tasks and incorporating global graph semantics for robust node embeddings.

Keywords:
Adaptive graph network represent learningGraph network analysisMulti-task learningMulti-view graph network

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

471
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

594

Related Experiment Videos

Last Updated: Aug 6, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

406
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

471
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

594

Area of Science:

  • Graph Network Analysis
  • Machine Learning
  • Data Mining

Background:

  • Existing graph network analysis methods often overlook task correlations and global graph information, leading to inefficiencies and suboptimal node embeddings.
  • Current approaches struggle to adaptively balance multiple analysis tasks, resulting in weak model fitting and repeated computations.
  • A significant limitation is the neglect of multiplex views' semantic information, hindering the learning of robust node representations.

Purpose of the Study:

  • To propose a multi-task, multi-view adaptive graph network representation learning model (M²agl) to address the limitations of existing methods.
  • To enhance graph network analysis by effectively integrating local and global graph features, and information across multiple views.
  • To improve node embedding robustness and model fitting by adaptively balancing multiple analysis tasks and leveraging inter-view dependencies.

Main Methods:

  • Utilized a graph convolutional network encoder combining adjacency and positive point-wise mutual information (PPMI) matrices for intra-view feature extraction.
  • Employed regularization and a view attention mechanism to capture inter-view interactions and adaptively fuse information from different graph views.
  • Trained the model using multiple graph network analysis tasks, with adaptive task importance adjustment via homoscedastic uncertainty for improved performance.

Main Results:

  • M²agl demonstrated superior performance on real-world attributed multiplex graph networks compared to existing approaches.
  • The model successfully extracted both local and global intra-view graph features, enhancing the quality of learned node embeddings.
  • Adaptive balancing of multiple tasks and effective fusion of multi-view information contributed to robust graph analysis results.

Conclusions:

  • M²agl offers an effective framework for multi-task, multi-view graph network representation learning.
  • The proposed method overcomes limitations in existing techniques by integrating diverse information sources and adaptively managing task importance.
  • M²agl significantly advances graph analysis by learning more robust node embeddings and achieving better overall performance.