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

A kernel approach for semisupervised metric learning.

Dit-Yan Yeung1, Hong Chang

  • 1Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong. dyyeung@cse.ust.hk

IEEE Transactions on Neural Networks
|February 7, 2007
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

Mixture of Cluster-Conditional LoRA Experts for Vision-Language Instruction Tuning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

An online forecasting-based fine-tuning pipeline for time-series anomaly prediction.

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

A Survey of Automated Data Augmentation for Image Classification: Learning to Compose, Mix, and Generate.

IEEE transactions on neural networks and learning systems·2023
Same author

Molecular Characterization and Expression Profiles of Cryptochrome Genes in a Long-Distance Migrant, Agrotis segetum (Lepidoptera: Noctuidae).

Journal of insect science (Online)·2019
Same author

[Role of hypomethylation of suppressor of cytokine signaling in T helper 17 cell/regulatory T cell imbalance in children with Henoch-Schönlein purpura].

Zhongguo dang dai er ke za zhi = Chinese journal of contemporary pediatrics·2019
Same author

Magnetic Properties and Carrier Transport of Ir<sub>0.9</sub>Mn<sub>1-x</sub>Sn<sub>1.1+x</sub>.

Materials (Basel, Switzerland)·2019
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a novel kernel approach for semisupervised metric learning, offering a convex optimization framework. This method shows promise for nonlinear metric learning tasks with limited supervision.

Area of Science:

  • Machine Learning
  • Computer Science

Background:

  • Distance function learning is established for supervised tasks.
  • Extending metric learning to semisupervised settings with weaker information is a recent challenge.
  • Existing semisupervised metric learning methods often rely on pairwise similarity/dissimilarity.

Purpose of the Study:

  • To propose a kernel approach for semisupervised metric learning.
  • To formulate metric learning as a convex kernel learning optimization problem.
  • To address nonlinear metric learning scenarios.

Main Methods:

  • Developed a kernel approach for semisupervised metric learning.
  • Formulated the problem as a convex optimization task for kernel learning.
  • Investigated two special cases: one with a closed-form solution, the other using iterative majorization.

Related Experiment Videos

Main Results:

  • The proposed kernel approach is formulated as a convex optimization problem, guaranteeing no local optima.
  • A closed-form solution was found for one special case.
  • An iterative majorization procedure was used to asymptotically estimate the optimal solution for the second case.
  • Experimental results on synthetic and real-world data demonstrated the approach's effectiveness.

Conclusions:

  • The proposed kernel approach is a promising method for semisupervised metric learning.
  • This technique is particularly effective for nonlinear metric learning tasks.
  • The convex optimization formulation ensures robust and reliable solutions.