TY - JOUR
T1 - Multilabel relationship learning
AU - Zhang, Yu
AU - Yeung, Dit Yan
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2013/7
Y1 - 2013/7
N2 - Multilabel learning problems are commonly found in many applications. A characteristic shared by many multilabel learning problems is that some labels have significant correlations between them. In this article, we propose a novel multilabel learning method, called MultiLabel Relationship Learning (MLRL), which extends the conventional support vector machine by explicitly learning and utilizing the relationships between labels. Specifically, we model the label relationships using a label covariance matrix and use it to define a new regularization term for the optimization problem. MLRL learns the model parameters and the label covariance matrix simultaneously based on a unified convex formulation. To solve the convex optimization problem, we use an alternating method in which each subproblem can be solved efficiently. The relationship between MLRL and two widely used maximum margin methods for multilabel learning is investigated. Moreover, we also propose a semisupervised extension of MLRL, called SSMLRL, to demonstrate how to make use of unlabeled data to help learn the label covariance matrix. Through experiments conducted on some multilabel applications, we find that MLRL not only gives higher classification accuracy but also has better interpretability as revealed by the label covariance matrix.
AB - Multilabel learning problems are commonly found in many applications. A characteristic shared by many multilabel learning problems is that some labels have significant correlations between them. In this article, we propose a novel multilabel learning method, called MultiLabel Relationship Learning (MLRL), which extends the conventional support vector machine by explicitly learning and utilizing the relationships between labels. Specifically, we model the label relationships using a label covariance matrix and use it to define a new regularization term for the optimization problem. MLRL learns the model parameters and the label covariance matrix simultaneously based on a unified convex formulation. To solve the convex optimization problem, we use an alternating method in which each subproblem can be solved efficiently. The relationship between MLRL and two widely used maximum margin methods for multilabel learning is investigated. Moreover, we also propose a semisupervised extension of MLRL, called SSMLRL, to demonstrate how to make use of unlabeled data to help learn the label covariance matrix. Through experiments conducted on some multilabel applications, we find that MLRL not only gives higher classification accuracy but also has better interpretability as revealed by the label covariance matrix.
KW - Label relationship
KW - Multilabel learning
UR - http://www.scopus.com/inward/record.url?scp=84896928346&partnerID=8YFLogxK
U2 - 10.1145/2499907.2499910
DO - 10.1145/2499907.2499910
M3 - Journal article
AN - SCOPUS:84896928346
SN - 1556-4681
VL - 7
JO - ACM Transactions on Knowledge Discovery from Data
JF - ACM Transactions on Knowledge Discovery from Data
IS - 2
M1 - 2499910
ER -