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 Experiment Videos

Graph embedding and extensions: a general framework for dimensionality reduction.

Shuicheng Yan1, Dong Xu, Benyu Zhang

  • 1Beckman Institute, University of Illinois at Urbana-Champaign, 405 North Mathews Avenue, Urbana, IL 61801, USA. scyan@ifp.uiuc.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 17, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

The Relationship between Meaning in Life and Mental Health in Chinese Undergraduates: The Mediating Roles of Self-Esteem and Interpersonal Trust.

Behavioral sciences (Basel, Switzerland)·2024
Same author

Dispositional Awe and Self-Worth in Chinese Undergraduates: The Suppressing Effects of Self-Concept Clarity and Small Self.

International journal of environmental research and public health·2023
Same author

Privacy-Preserving Multi-Class Support Vector Machine Model on Medical Diagnosis.

IEEE journal of biomedical and health informatics·2022
Same author

Updatable privacy-preserving <math></math> -nearest neighbor query in location-based s-ervice.

Peer-to-peer networking and applications·2022
Same author

Classification of lung cancer using ensemble-based feature selection and machine learning methods.

Molecular bioSystems·2014
Same author

Resveratrol possesses protective effects in a pristane-induced lupus mouse model.

PloS one·2014
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study unifies dimensionality reduction algorithms using graph embedding. A new supervised method, Marginal Fisher Analysis (MFA), enhances data analysis and outperforms Linear Discriminant Analysis (LDA) in face recognition.

Area of Science:

  • Machine Learning
  • Data Science
  • Computer Vision

Background:

  • Numerous dimensionality reduction algorithms exist, stemming from diverse statistical and geometric theories.
  • These algorithms offer varied solutions but lack a unified theoretical framework.

Purpose of the Study:

  • To introduce a general graph embedding framework to unify existing dimensionality reduction algorithms.
  • To propose a novel supervised dimensionality reduction algorithm, Marginal Fisher Analysis (MFA).

Main Methods:

  • Developed a general graph embedding formulation to encompass various dimensionality reduction techniques.
  • Proposed MFA, defining intrinsic and penalty graphs for intraclass compactness and interclass separability.
  • Utilized kernel and tensor extensions for enhanced performance.

Related Experiment Videos

Main Results:

  • The graph embedding framework successfully unifies diverse dimensionality reduction algorithms.
  • Marginal Fisher Analysis (MFA) demonstrates superiority over Linear Discriminant Analysis (LDA).
  • MFA shows improved performance in face recognition experiments compared to LDA and its extensions.

Conclusions:

  • Graph embedding provides a unified platform for understanding and developing dimensionality reduction algorithms.
  • MFA effectively addresses limitations of traditional methods like LDA, particularly in complex data distributions.
  • The proposed MFA algorithm offers significant advantages for supervised dimensionality reduction tasks, especially in pattern recognition applications like face recognition.