A scalable kernel-based semisupervised metric learning algorithm with out-of-sample generalization ability

Authors:
Dit-Yan Yeung;Hong Chang;Guang Dai
Affiliations:
Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, China. dyyeung@cse.ust.hk;Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China. changhong@ict.ac.cn;Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, China. daiguang@cse.ust.hk
Venue:
Neural Computation
Year:
2008

Citing 13
Cited 6

Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
Constrained K-means Clustering with Background Knowledge

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Clustering with Instance-level Constraints

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Learning the Kernel Matrix with Semi-Definite Programming

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
The em algorithm for kernel matrix completion with auxiliary data

The Journal of Machine Learning Research
Think globally, fit locally: unsupervised learning of low dimensional manifolds

The Journal of Machine Learning Research
Integrating constraints and metric learning in semi-supervised clustering

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Bayesian inference for transductive learning of kernel matrix using the Tanner-Wong data augmentation algorithm

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Boosting margin based distance functions for clustering

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Locally linear metric adaptation for semi-supervised clustering

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Leveraging Social Networks to Fight Spam

Computer
Learning a Mahalanobis Metric from Equivalence Constraints

The Journal of Machine Learning Research
Generalized Low Rank Approximations of Matrices

Machine Learning

Kernel-based metric learning for semi-supervised clustering

Neurocomputing
Transfer metric learning by learning task relationships

Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Learning low-rank kernel matrices for constrained clustering

Neurocomputing
Multiview Metric Learning with Global Consistency and Local Smoothness

ACM Transactions on Intelligent Systems and Technology (TIST)
Transfer Metric Learning with Semi-Supervised Extension

ACM Transactions on Intelligent Systems and Technology (TIST)
Discriminant sparse neighborhood preserving embedding for face recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In recent years, metric learning in the semisupervised setting has aroused a lot of research interest. One type of semisupervised metric learning utilizes supervisory information in the form of pairwise similarity or dissimilarity constraints. However, most methods proposed so far are either limited to linear metric learning or unable to scale well with the data set size. In this letter, we propose a nonlinear metric learning method based on the kernel approach. By applying low-rank approximation to the kernel matrix, our method can handle significantly larger data sets. Moreover, our low-rank approximation scheme can naturally lead to out-of-sample generalization. Experiments performed on both artificial and real-world data show very promising results.