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

Associative Learning01:27

Associative Learning

285
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...
285
Protein Networks02:26

Protein Networks

3.9K
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,...
3.9K
Bar Graph01:07

Bar Graph

16.0K
A bar graph is also called a bar chart and consists of bars that are separated from each other. It either uses horizontal or vertical bars to show comparisons among categories. The bars can be rectangles, or they can be rectangular boxes (used in three-dimensional plots). One axis of the graph represents the specific categories being compared, and the other axis shows a discrete value. In this graph, the length of the bar for each category is proportional to the number or percent of individuals...
16.0K
Normal and Tangetial Components: Problem Solving01:24

Normal and Tangetial Components: Problem Solving

169
Consider a man with a mass of 70 kg seated in a chair connected to a pin support through a member BC. If the man maintains an upright position, the task is to determine the horizontal and vertical reactions of the chair on the man when the member makes a 45° angle with the horizontal. At this moment, the man has a speed of 5 m/s, increasing at a rate of 1 m/s².
169
Attribution Theory00:56

Attribution Theory

12.9K
Behavior is a product of both the situation (e.g., cultural influences, social roles, and the presence of bystanders) and of the person (e.g., personality characteristics). Subfields of psychology tend to focus on one influence or behavior over others. Situationism is the view that our behavior and actions are determined by our immediate environment and surroundings. In contrast, dispositionism holds that our behavior is determined by internal factors (Heider, 1958).
12.9K
Multiple Bar Graph01:07

Multiple Bar Graph

5.1K
As the name suggests, a multiple bar graph is the same as a bar graph but has multiple bars to depict relationships between different data values. One can include as many parameters as possible. However, each parameter must have the same unit of measurement.
Each bar or column in the multiple bar graph represents a data value. These graphs are used primarily in interrelating two or more sets of data. The categories of different kinds of data are listed along the horizontal or x-axis, whereas...
5.1K

You might also read

Related Articles

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

Sort by
Same author

Learning dynamic graph representations through timespan view contrasts.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Corrigendum: Tree-shrub-grass composite woodland better facilitates emotional recovery in college students emotion better than other plant communities.

Frontiers in psychology·2024
Same author

Statins improve cardiac endothelial function to prevent heart failure with preserved ejection fraction through upregulating circRNA-RBCK1.

Nature communications·2024
Same author

WITHDRAWN: Impact of a Clinical Nursing Teaching Model Based on Institutional Cooperation on Teaching Quality of Nursing Programs in Colleges and Universities and Effectiveness of Internship for Undergraduate Nurses.

Alternative therapies in health and medicine·2024
Same author

Spatially resolved single-cell atlas of ascidian endostyle provides insight into the origin of vertebrate pharyngeal organs.

Science advances·2024
Same author

Resolving neuroinflammatory and social deficits in ASD model mice: Dexmedetomidine downregulates NF-κB/IL-6 pathway via α2AR.

Brain, behavior, and immunity·2024

Related Experiment Video

Updated: May 30, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K

When bipartite graph learning meets anomaly detection in attributed networks: Understand abnormalities from each

Zhen Peng1, Yunfan Wang2, Qika Lin3

  • 1School of Computer Science and Technology, Xi'an Jiaotong University, China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 25, 2025
PubMed
Summary

Eagle, a novel deep framework for anomaly detection in attributed networks, analyzes anomalies at a fine-grained feature level. It disentangles instances and attributes, enabling better understanding of abnormalities across different feature combinations.

Keywords:
Bipartite graph modelingGraph anomaly detectionSelf-supervised learning

More Related Videos

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
08:43

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

7.8K
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

984

Related Experiment Videos

Last Updated: May 30, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
08:43

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

7.8K
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

984

Area of Science:

  • Graph Neural Networks
  • Machine Learning
  • Data Mining

Background:

  • Anomaly detection in attributed networks is crucial across various applications.
  • Existing graph neural network methods often aggregate node attributes, limiting fine-grained analysis.
  • There is a need for methods that can characterize anomalies based on individual feature dimensions.

Purpose of the Study:

  • To propose Eagle, a deep framework for anomaly detection in attributed networks.
  • To enable fine-grained analysis of anomalies by disentangling node instances and their attributes.
  • To provide a user-friendly approach for understanding abnormalities from multiple feature perspectives.

Main Methods:

  • Eagle utilizes a bipartite graph structure, separating instances and attributes into disjoint node sets.
  • It models the attributed network as an intra-connected bipartite graph with two relation types.
  • A self-supervised edge-level prediction task, affinity inference, is employed for learning.

Main Results:

  • Eagle demonstrates effectiveness in both transductive and inductive anomaly detection settings.
  • The framework allows for the characterization of anomalies across individual attribute dimensions.
  • Case studies confirm the user-friendliness and interpretability of Eagle.

Conclusions:

  • Eagle offers an effective approach for fine-grained anomaly detection in attributed networks.
  • The disentangled representation and affinity inference task provide interpretable insights into anomalies.
  • Eagle enhances the understanding of network abnormalities by considering feature combinations.